Eval bug: WebUI incorrectly displays that images not supported for Qwen VL

[jagusztinl]

Name and Version

build: 7036 (017ecee) with cc (Ubuntu 14.2.0-4ubuntu2~24.04) 14.2.0 for aarch64-linux-gnu

Operating systems

Linux

GGML backends

CPU

Hardware

Azure Cobalt

Models

Qwen3-VL-235B-A22B-Instruct-IQ4_NL-00001-of-00003.gguf

Problem description & steps to reproduce

Qwen VL model not recognized as vision model for images.

First Bad Commit

No response

Relevant log output

build: 7036 (017eceed6) with cc (Ubuntu 14.2.0-4ubuntu2~24.04) 14.2.0 for aarch64-linux-gnu
system info: n_threads = 64, n_threads_batch = 64, total_threads = 64

system_info: n_threads = 64 (n_threads_batch = 64) / 64 | CPU : NEON = 1 | ARM_FMA = 1 | FP16_VA = 1 | MATMUL_INT8 = 1 | SVE = 1 | DOTPROD = 1 | SVE_CNT = 16 | OPENMP = 1 | REPACK = 1 |

main: binding port with default address family
main: HTTP server is listening, hostname: 0.0.0.0, port: 8082, http threads: 63
main: loading model
srv    load_model: loading model '/home/alerant/models/IQ4_NL/Qwen3-VL-235B-A22B-Instruct-IQ4_NL-00001-of-00003.gguf'
llama_model_loader: additional 2 GGUFs metadata loaded.
llama_model_loader: loaded meta data with 48 key-value pairs and 1131 tensors from /home/alerant/models/IQ4_NL/Qwen3-VL-235B-A22B-Instruct-IQ4_NL-00001-of-00003.gguf (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv   0:                       general.architecture str              = qwen3vlmoe
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = Qwen3-Vl-235B-A22B-Instruct
llama_model_loader: - kv   3:                           general.finetune str              = Instruct
llama_model_loader: - kv   4:                           general.basename str              = Qwen3-Vl-235B-A22B-Instruct
llama_model_loader: - kv   5:                       general.quantized_by str              = Unsloth
llama_model_loader: - kv   6:                         general.size_label str              = 235B-A22B
llama_model_loader: - kv   7:                            general.license str              = apache-2.0
llama_model_loader: - kv   8:                           general.repo_url str              = https://huggingface.co/unsloth
llama_model_loader: - kv   9:                   general.base_model.count u32              = 1
llama_model_loader: - kv  10:                  general.base_model.0.name str              = Qwen3 VL 235B A22B Instruct
llama_model_loader: - kv  11:          general.base_model.0.organization str              = Qwen
llama_model_loader: - kv  12:              general.base_model.0.repo_url str              = https://huggingface.co/Qwen/Qwen3-VL-...
llama_model_loader: - kv  13:                               general.tags arr[str,1]       = ["unsloth"]
llama_model_loader: - kv  14:                     qwen3vlmoe.block_count u32              = 94
llama_model_loader: - kv  15:                  qwen3vlmoe.context_length u32              = 262144
llama_model_loader: - kv  16:                qwen3vlmoe.embedding_length u32              = 4096
llama_model_loader: - kv  17:             qwen3vlmoe.feed_forward_length u32              = 12288
llama_model_loader: - kv  18:            qwen3vlmoe.attention.head_count u32              = 64
llama_model_loader: - kv  19:         qwen3vlmoe.attention.head_count_kv u32              = 4
llama_model_loader: - kv  20:                  qwen3vlmoe.rope.freq_base f32              = 5000000.000000
llama_model_loader: - kv  21: qwen3vlmoe.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  22:               qwen3vlmoe.expert_used_count u32              = 8
llama_model_loader: - kv  23:            qwen3vlmoe.attention.key_length u32              = 128
llama_model_loader: - kv  24:          qwen3vlmoe.attention.value_length u32              = 128
llama_model_loader: - kv  25:                    qwen3vlmoe.expert_count u32              = 128
llama_model_loader: - kv  26:      qwen3vlmoe.expert_feed_forward_length u32              = 1536
llama_model_loader: - kv  27:         qwen3vlmoe.rope.dimension_sections arr[i32,4]       = [24, 20, 20, 0]
llama_model_loader: - kv  28:              qwen3vlmoe.n_deepstack_layers u32              = 3
llama_model_loader: - kv  29:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  30:                         tokenizer.ggml.pre str              = qwen2
llama_model_loader: - kv  31:                      tokenizer.ggml.tokens arr[str,151936]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  32:                  tokenizer.ggml.token_type arr[i32,151936]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  33:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  34:                tokenizer.ggml.eos_token_id u32              = 151645
llama_model_loader: - kv  35:            tokenizer.ggml.padding_token_id u32              = 151654
llama_model_loader: - kv  36:                tokenizer.ggml.bos_token_id u32              = 151643
llama_model_loader: - kv  37:               tokenizer.ggml.add_bos_token bool             = false
llama_model_loader: - kv  38:                    tokenizer.chat_template str              = {%- if tools %}\n    {{- '<|im_start|>...
llama_model_loader: - kv  39:               general.quantization_version u32              = 2
llama_model_loader: - kv  40:                          general.file_type u32              = 25
llama_model_loader: - kv  41:                      quantize.imatrix.file str              = Qwen3-VL-235B-A22B-Instruct-GGUF/imat...
llama_model_loader: - kv  42:                   quantize.imatrix.dataset str              = unsloth_calibration_Qwen3-VL-235B-A22...
llama_model_loader: - kv  43:             quantize.imatrix.entries_count u32              = 752
llama_model_loader: - kv  44:              quantize.imatrix.chunks_count u32              = 154
llama_model_loader: - kv  45:                                   split.no u16              = 0
llama_model_loader: - kv  46:                        split.tensors.count i32              = 1131
llama_model_loader: - kv  47:                                split.count u16              = 3
llama_model_loader: - type  f32:  471 tensors
llama_model_loader: - type q4_K:    1 tensors
llama_model_loader: - type q5_K:   94 tensors
llama_model_loader: - type q6_K:    1 tensors
llama_model_loader: - type iq4_nl:  564 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = IQ4_NL - 4.5 bpw
print_info: file size   = 123.49 GiB (4.51 BPW)
load: printing all EOG tokens:
load:   - 151643 ('<|endoftext|>')
load:   - 151645 ('<|im_end|>')
load:   - 151662 ('<|fim_pad|>')
load:   - 151663 ('<|repo_name|>')
load:   - 151664 ('<|file_sep|>')
load: special tokens cache size = 26
load: token to piece cache size = 0.9311 MB
print_info: arch             = qwen3vlmoe
print_info: vocab_only       = 0
print_info: n_ctx_train      = 262144
print_info: n_embd           = 4096
print_info: n_embd_inp       = 16384
print_info: n_layer          = 94
print_info: n_head           = 64
print_info: n_head_kv        = 4
print_info: n_rot            = 128
print_info: n_swa            = 0
print_info: is_swa_any       = 0
print_info: n_embd_head_k    = 128
print_info: n_embd_head_v    = 128
print_info: n_gqa            = 16
print_info: n_embd_k_gqa     = 512
print_info: n_embd_v_gqa     = 512
print_info: f_norm_eps       = 0.0e+00
print_info: f_norm_rms_eps   = 1.0e-06
print_info: f_clamp_kqv      = 0.0e+00
print_info: f_max_alibi_bias = 0.0e+00
print_info: f_logit_scale    = 0.0e+00
print_info: f_attn_scale     = 0.0e+00
print_info: n_ff             = 12288
print_info: n_expert         = 128
print_info: n_expert_used    = 8
print_info: n_expert_groups  = 0
print_info: n_group_used     = 0
print_info: causal attn      = 1
print_info: pooling type     = 0
print_info: rope type        = 40
print_info: rope scaling     = linear
print_info: freq_base_train  = 5000000.0
print_info: freq_scale_train = 1
print_info: n_ctx_orig_yarn  = 262144
print_info: rope_finetuned   = unknown
print_info: mrope sections   = [24, 20, 20, 0]
print_info: model type       = 235B.A22B
print_info: model params     = 235.09 B
print_info: general.name     = Qwen3-Vl-235B-A22B-Instruct
print_info: n_ff_exp         = 1536
print_info: vocab type       = BPE
print_info: n_vocab          = 151936
print_info: n_merges         = 151387
print_info: BOS token        = 151643 '<|endoftext|>'
print_info: EOS token        = 151645 '<|im_end|>'
print_info: EOT token        = 151645 '<|im_end|>'
print_info: PAD token        = 151654 '<|vision_pad|>'
print_info: LF token         = 198 'Ċ'
print_info: FIM PRE token    = 151659 '<|fim_prefix|>'
print_info: FIM SUF token    = 151661 '<|fim_suffix|>'
print_info: FIM MID token    = 151660 '<|fim_middle|>'
print_info: FIM PAD token    = 151662 '<|fim_pad|>'
print_info: FIM REP token    = 151663 '<|repo_name|>'
print_info: FIM SEP token    = 151664 '<|file_sep|>'
print_info: EOG token        = 151643 '<|endoftext|>'
print_info: EOG token        = 151645 '<|im_end|>'
print_info: EOG token        = 151662 '<|fim_pad|>'
print_info: EOG token        = 151663 '<|repo_name|>'
print_info: EOG token        = 151664 '<|file_sep|>'
print_info: max token length = 256
load_tensors: loading model tensors, this can take a while... (mmap = true)
load_tensors: offloading 94 repeating layers to GPU
load_tensors: offloading output layer to GPU
load_tensors: offloaded 95/95 layers to GPU
load_tensors:   CPU_Mapped model buffer size = 47637.86 MiB
load_tensors:   CPU_Mapped model buffer size = 46780.64 MiB
load_tensors:   CPU_Mapped model buffer size = 30307.12 MiB
load_tensors:   CPU_REPACK model buffer size = 125313.75 MiB
....................................................................................................
llama_context: constructing llama_context
llama_context: n_ctx is not divisible by n_seq_max - rounding down to 262656
llama_context: n_seq_max     = 3
llama_context: n_ctx         = 262656
llama_context: n_ctx_seq     = 87552
llama_context: n_batch       = 1014
llama_context: n_ubatch      = 1014
llama_context: causal_attn   = 1
llama_context: flash_attn    = enabled
llama_context: kv_unified    = false
llama_context: freq_base     = 5000000.0
llama_context: freq_scale    = 1
llama_context: n_ctx_seq (87552) < n_ctx_train (262144) -- the full capacity of the model will not be utilized
llama_context:        CPU  output buffer size =     1.74 MiB
llama_kv_cache:        CPU KV buffer size = 25617.94 MiB
llama_kv_cache: size = 25617.94 MiB ( 87552 cells,  94 layers,  3/3 seqs), K (q8_0): 12808.97 MiB, V (q8_0): 12808.97 MiB
llama_context:        CPU compute buffer size =   889.73 MiB
llama_context: graph nodes  = 6117
llama_context: graph splits = 1
common_init_from_params: added <|endoftext|> logit bias = -inf
common_init_from_params: added <|im_end|> logit bias = -inf
common_init_from_params: added <|fim_pad|> logit bias = -inf
common_init_from_params: added <|repo_name|> logit bias = -inf
common_init_from_params: added <|file_sep|> logit bias = -inf
common_init_from_params: setting dry_penalty_last_n to ctx_size = 262656
common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable)
srv          init: initializing slots, n_slots = 3
slot         init: id  0 | task -1 | new slot, n_ctx = 87552
slot         init: id  1 | task -1 | new slot, n_ctx = 87552
slot         init: id  2 | task -1 | new slot, n_ctx = 87552
srv          init: prompt cache is enabled, size limit: 8192 MiB
srv          init: use `--cache-ram 0` to disable the prompt cache
srv          init: for more info see https://github.com/ggml-org/llama.cpp/pull/16391
srv          init: thinking = 0
main: model loaded

[jagusztinl]

[ngxson]

You did not load the mmproj file: https://huggingface.co/unsloth/Qwen3-VL-235B-A22B-Instruct-GGUF/blob/main/mmproj-F16.gguf

[jagusztinl]

Unfortunately the --mmproj did not solve it.

llama-server --port 8082 -fa on --jinja -t 64 --temp 0.6 --min-p 0.0 --top-p 0.95 --top-k 20 --parallel 3 --cont-batching --host 0.0.0.0 -ub 1024 -b 1014 -c 0 -ctk q8_0 -ctv q8_0 -m $HOME/models/IQ4_NL/Qwen3-VL-235B-A22B-Instruct-IQ4_NL-00001-of-00003.gguf --mmproj mmproj-F16.gguf
build: 7036 (017ecee) with cc (Ubuntu 14.2.0-4ubuntu2~24.04) 14.2.0 for aarch64-linux-gnu
system info: n_threads = 64, n_threads_batch = 64, total_threads = 64

system_info: n_threads = 64 (n_threads_batch = 64) / 64 | CPU : NEON = 1 | ARM_FMA = 1 | FP16_VA = 1 | MATMUL_INT8 = 1 | SVE = 1 | DOTPROD = 1 | SVE_CNT = 16 | OPENMP = 1 | REPACK = 1 |

main: binding port with default address family
main: HTTP server is listening, hostname: 0.0.0.0, port: 8082, http threads: 63
main: loading model
srv load_model: loading model '/home/alerant/models/IQ4_NL/Qwen3-VL-235B-A22B-Instruct-IQ4_NL-00001-of-00003.gguf'
llama_model_loader: additional 2 GGUFs metadata loaded.
llama_model_loader: loaded meta data with 48 key-value pairs and 1131 tensors from /home/alerant/models/IQ4_NL/Qwen3-VL-235B-A22B-Instruct-IQ4_NL-00001-of-00003.gguf (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv 0: general.architecture str = qwen3vlmoe
llama_model_loader: - kv 1: general.type str = model
llama_model_loader: - kv 2: general.name str = Qwen3-Vl-235B-A22B-Instruct
llama_model_loader: - kv 3: general.finetune str = Instruct
llama_model_loader: - kv 4: general.basename str = Qwen3-Vl-235B-A22B-Instruct
llama_model_loader: - kv 5: general.quantized_by str = Unsloth
llama_model_loader: - kv 6: general.size_label str = 235B-A22B
llama_model_loader: - kv 7: general.license str = apache-2.0
llama_model_loader: - kv 8: general.repo_url str = https://huggingface.co/unsloth
llama_model_loader: - kv 9: general.base_model.count u32 = 1
llama_model_loader: - kv 10: general.base_model.0.name str = Qwen3 VL 235B A22B Instruct
llama_model_loader: - kv 11: general.base_model.0.organization str = Qwen
llama_model_loader: - kv 12: general.base_model.0.repo_url str = https://huggingface.co/Qwen/Qwen3-VL-...
llama_model_loader: - kv 13: general.tags arr[str,1] = ["unsloth"]
llama_model_loader: - kv 14: qwen3vlmoe.block_count u32 = 94
llama_model_loader: - kv 15: qwen3vlmoe.context_length u32 = 262144
llama_model_loader: - kv 16: qwen3vlmoe.embedding_length u32 = 4096
llama_model_loader: - kv 17: qwen3vlmoe.feed_forward_length u32 = 12288
llama_model_loader: - kv 18: qwen3vlmoe.attention.head_count u32 = 64
llama_model_loader: - kv 19: qwen3vlmoe.attention.head_count_kv u32 = 4
llama_model_loader: - kv 20: qwen3vlmoe.rope.freq_base f32 = 5000000.000000
llama_model_loader: - kv 21: qwen3vlmoe.attention.layer_norm_rms_epsilon f32 = 0.000001
llama_model_loader: - kv 22: qwen3vlmoe.expert_used_count u32 = 8
llama_model_loader: - kv 23: qwen3vlmoe.attention.key_length u32 = 128
llama_model_loader: - kv 24: qwen3vlmoe.attention.value_length u32 = 128
llama_model_loader: - kv 25: qwen3vlmoe.expert_count u32 = 128
llama_model_loader: - kv 26: qwen3vlmoe.expert_feed_forward_length u32 = 1536
llama_model_loader: - kv 27: qwen3vlmoe.rope.dimension_sections arr[i32,4] = [24, 20, 20, 0]
llama_model_loader: - kv 28: qwen3vlmoe.n_deepstack_layers u32 = 3
llama_model_loader: - kv 29: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 30: tokenizer.ggml.pre str = qwen2
llama_model_loader: - kv 31: tokenizer.ggml.tokens arr[str,151936] = ["!", """, "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 32: tokenizer.ggml.token_type arr[i32,151936] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 33: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv 34: tokenizer.ggml.eos_token_id u32 = 151645
llama_model_loader: - kv 35: tokenizer.ggml.padding_token_id u32 = 151654
llama_model_loader: - kv 36: tokenizer.ggml.bos_token_id u32 = 151643
llama_model_loader: - kv 37: tokenizer.ggml.add_bos_token bool = false
llama_model_loader: - kv 38: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>...
llama_model_loader: - kv 39: general.quantization_version u32 = 2
llama_model_loader: - kv 40: general.file_type u32 = 25
llama_model_loader: - kv 41: quantize.imatrix.file str = Qwen3-VL-235B-A22B-Instruct-GGUF/imat...
llama_model_loader: - kv 42: quantize.imatrix.dataset str = unsloth_calibration_Qwen3-VL-235B-A22...
llama_model_loader: - kv 43: quantize.imatrix.entries_count u32 = 752
llama_model_loader: - kv 44: quantize.imatrix.chunks_count u32 = 154
llama_model_loader: - kv 45: split.no u16 = 0
llama_model_loader: - kv 46: split.tensors.count i32 = 1131
llama_model_loader: - kv 47: split.count u16 = 3
llama_model_loader: - type f32: 471 tensors
llama_model_loader: - type q4_K: 1 tensors
llama_model_loader: - type q5_K: 94 tensors
llama_model_loader: - type q6_K: 1 tensors
llama_model_loader: - type iq4_nl: 564 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = IQ4_NL - 4.5 bpw
print_info: file size = 123.49 GiB (4.51 BPW)
load: printing all EOG tokens:
load: - 151643 ('<|endoftext|>')
load: - 151645 ('<|im_end|>')
load: - 151662 ('<|fim_pad|>')
load: - 151663 ('<|repo_name|>')
load: - 151664 ('<|file_sep|>')
load: special tokens cache size = 26
load: token to piece cache size = 0.9311 MB
print_info: arch = qwen3vlmoe
print_info: vocab_only = 0
print_info: n_ctx_train = 262144
print_info: n_embd = 4096
print_info: n_embd_inp = 16384
print_info: n_layer = 94
print_info: n_head = 64
print_info: n_head_kv = 4
print_info: n_rot = 128
print_info: n_swa = 0
print_info: is_swa_any = 0
print_info: n_embd_head_k = 128
print_info: n_embd_head_v = 128
print_info: n_gqa = 16
print_info: n_embd_k_gqa = 512
print_info: n_embd_v_gqa = 512
print_info: f_norm_eps = 0.0e+00
print_info: f_norm_rms_eps = 1.0e-06
print_info: f_clamp_kqv = 0.0e+00
print_info: f_max_alibi_bias = 0.0e+00
print_info: f_logit_scale = 0.0e+00
print_info: f_attn_scale = 0.0e+00
print_info: n_ff = 12288
print_info: n_expert = 128
print_info: n_expert_used = 8
print_info: n_expert_groups = 0
print_info: n_group_used = 0
print_info: causal attn = 1
print_info: pooling type = 0
print_info: rope type = 40
print_info: rope scaling = linear
print_info: freq_base_train = 5000000.0
print_info: freq_scale_train = 1
print_info: n_ctx_orig_yarn = 262144
print_info: rope_finetuned = unknown
print_info: mrope sections = [24, 20, 20, 0]
print_info: model type = 235B.A22B
print_info: model params = 235.09 B
print_info: general.name = Qwen3-Vl-235B-A22B-Instruct
print_info: n_ff_exp = 1536
print_info: vocab type = BPE
print_info: n_vocab = 151936
print_info: n_merges = 151387
print_info: BOS token = 151643 '<|endoftext|>'
print_info: EOS token = 151645 '<|im_end|>'
print_info: EOT token = 151645 '<|im_end|>'
print_info: PAD token = 151654 '<|vision_pad|>'
print_info: LF token = 198 'Ċ'
print_info: FIM PRE token = 151659 '<|fim_prefix|>'
print_info: FIM SUF token = 151661 '<|fim_suffix|>'
print_info: FIM MID token = 151660 '<|fim_middle|>'
print_info: FIM PAD token = 151662 '<|fim_pad|>'
print_info: FIM REP token = 151663 '<|repo_name|>'
print_info: FIM SEP token = 151664 '<|file_sep|>'
print_info: EOG token = 151643 '<|endoftext|>'
print_info: EOG token = 151645 '<|im_end|>'
print_info: EOG token = 151662 '<|fim_pad|>'
print_info: EOG token = 151663 '<|repo_name|>'
print_info: EOG token = 151664 '<|file_sep|>'
print_info: max token length = 256
load_tensors: loading model tensors, this can take a while... (mmap = true)
load_tensors: offloading 94 repeating layers to GPU
load_tensors: offloading output layer to GPU
load_tensors: offloaded 95/95 layers to GPU
load_tensors: CPU_Mapped model buffer size = 47637.86 MiB
load_tensors: CPU_Mapped model buffer size = 46780.64 MiB
load_tensors: CPU_Mapped model buffer size = 30307.12 MiB
load_tensors: CPU_REPACK model buffer size = 125313.75 MiB
....................................................................................................
llama_context: constructing llama_context
llama_context: n_ctx is not divisible by n_seq_max - rounding down to 262656
llama_context: n_seq_max = 3
llama_context: n_ctx = 262656
llama_context: n_ctx_seq = 87552
llama_context: n_batch = 1014
llama_context: n_ubatch = 1014
llama_context: causal_attn = 1
llama_context: flash_attn = enabled
llama_context: kv_unified = false
llama_context: freq_base = 5000000.0
llama_context: freq_scale = 1
llama_context: n_ctx_seq (87552) < n_ctx_train (262144) -- the full capacity of the model will not be utilized
llama_context: CPU output buffer size = 1.74 MiB
llama_kv_cache: CPU KV buffer size = 25617.94 MiB
llama_kv_cache: size = 25617.94 MiB ( 87552 cells, 94 layers, 3/3 seqs), K (q8_0): 12808.97 MiB, V (q8_0): 12808.97 MiB
llama_context: CPU compute buffer size = 889.73 MiB
llama_context: graph nodes = 6117
llama_context: graph splits = 1
common_init_from_params: added <|endoftext|> logit bias = -inf
common_init_from_params: added <|im_end|> logit bias = -inf
common_init_from_params: added <|fim_pad|> logit bias = -inf
common_init_from_params: added <|repo_name|> logit bias = -inf
common_init_from_params: added <|file_sep|> logit bias = -inf
common_init_from_params: setting dry_penalty_last_n to ctx_size = 262656
common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable)
clip_model_loader: model name: Qwen3-Vl-235B-A22B-Instruct
clip_model_loader: description:
clip_model_loader: GGUF version: 3
clip_model_loader: alignment: 32
clip_model_loader: n_tensors: 352
clip_model_loader: n_kv: 31

clip_model_loader: has vision encoder
clip_ctx: CLIP using CPU backend
load_hparams: Qwen-VL models require at minimum 1024 image tokens to function correctly on grounding tasks
load_hparams: if you encounter problems with accuracy, try adding --image-min-tokens 1024
load_hparams: more info: #16842

load_hparams: projector: qwen3vl_merger
load_hparams: n_embd: 1152
load_hparams: n_head: 16
load_hparams: n_ff: 4304
load_hparams: n_layer: 27
load_hparams: ffn_op: gelu
load_hparams: projection_dim: 4096

--- vision hparams ---
load_hparams: image_size: 768
load_hparams: patch_size: 16
load_hparams: has_llava_proj: 0
load_hparams: minicpmv_version: 0
load_hparams: n_merge: 2
load_hparams: n_wa_pattern: 0
load_hparams: image_min_pixels: 8192
load_hparams: image_max_pixels: 4194304

load_hparams: model size: 1105.32 MiB
load_hparams: metadata size: 0.12 MiB
alloc_compute_meta: warmup with image size = 1472 x 1472
alloc_compute_meta: CPU compute buffer size = 372.08 MiB
alloc_compute_meta: graph splits = 1, nodes = 853
warmup: flash attention is enabled
srv load_model: loaded multimodal model, 'mmproj-F16.gguf'
srv init: initializing slots, n_slots = 3
slot init: id 0 | task -1 | new slot, n_ctx = 87552
slot init: id 1 | task -1 | new slot, n_ctx = 87552
slot init: id 2 | task -1 | new slot, n_ctx = 87552
srv init: prompt cache is enabled, size limit: 8192 MiB
srv init: use --cache-ram 0 to disable the prompt cache
srv init: for more info see #16391
srv init: thinking = 0
main: model loaded
main: chat template, chat_template: {%- if tools %}
{{- '<|im_start|>system\n' }}
{%- if messages[0].role == 'system' %}
{%- if messages[0].content is string %}
{{- messages[0].content }}
{%- else %}
{%- for content in messages[0].content %}
{%- if 'text' in content %}
{{- content.text }}
{%- endif %}
{%- endfor %}
{%- endif %}
{{- '\n\n' }}
{%- endif %}
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }}
{%- for tool in tools %}
{{- "\n" }}
{{- tool | tojson }}
{%- endfor %}
{{- "\n\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{"name": , "arguments": }\n</tool_call><|im_end|>\n" }}
{%- else %}
{%- if messages[0].role == 'system' %}
{{- '<|im_start|>system\n' }}
{%- if messages[0].content is string %}
{{- messages[0].content }}
{%- else %}
{%- for content in messages[0].content %}
{%- if 'text' in content %}
{{- content.text }}
{%- endif %}
{%- endfor %}
{%- endif %}
{{- '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- set image_count = namespace(value=0) %}
{%- set video_count = namespace(value=0) %}
{%- for message in messages %}
{%- if message.role == "user" %}
{{- '<|im_start|>' + message.role + '\n' }}
{%- if message.content is string %}
{{- message.content }}
{%- else %}
{%- for content in message.content %}
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
{%- set image_count.value = image_count.value + 1 %}
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
<|vision_start|><|image_pad|><|vision_end|>
{%- elif content.type == 'video' or 'video' in content %}
{%- set video_count.value = video_count.value + 1 %}
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
<|vision_start|><|video_pad|><|vision_end|>
{%- elif 'text' in content %}
{{- content.text }}
{%- endif %}
{%- endfor %}
{%- endif %}
{{- '<|im_end|>\n' }}
{%- elif message.role == "assistant" %}
{{- '<|im_start|>' + message.role + '\n' }}
{%- if message.content is string %}
{{- message.content }}
{%- else %}
{%- for content_item in message.content %}
{%- if 'text' in content_item %}
{{- content_item.text }}
{%- endif %}
{%- endfor %}
{%- endif %}
{%- if message.tool_calls %}
{%- for tool_call in message.tool_calls %}
{%- if (loop.first and message.content) or (not loop.first) %}
{{- '\n' }}
{%- endif %}
{%- if tool_call.function %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{{- '<tool_call>\n{"name": "' }}
{{- tool_call.name }}
{{- '", "arguments": ' }}
{%- if tool_call.arguments is string %}
{{- tool_call.arguments }}
{%- else %}
{{- tool_call.arguments | tojson }}
{%- endif %}
{{- '}\n</tool_call>' }}
{%- endfor %}
{%- endif %}
{{- '<|im_end|>\n' }}
{%- elif message.role == "tool" %}
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
{{- '<|im_start|>user' }}
{%- endif %}
{{- '\n<tool_response>\n' }}
{%- if message.content is string %}
{{- message.content }}
{%- else %}
{%- for content in message.content %}
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
{%- set image_count.value = image_count.value + 1 %}
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
<|vision_start|><|image_pad|><|vision_end|>
{%- elif content.type == 'video' or 'video' in content %}
{%- set video_count.value = video_count.value + 1 %}
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
<|vision_start|><|video_pad|><|vision_end|>
{%- elif 'text' in content %}
{{- content.text }}
{%- endif %}
{%- endfor %}
{%- endif %}
{{- '\n</tool_response>' }}
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
{{- '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|im_start|>assistant\n' }}
{%- endif %}
, example_format: '<|im_start|>system
You are a helpful assistant<|im_end|>
<|im_start|>user
Hello<|im_end|>
<|im_start|>assistant
Hi there<|im_end|>
<|im_start|>user
How are you?<|im_end|>
<|im_start|>assistant
'
main: server is listening on http://0.0.0.0:8082 - starting the main loop

[jagusztinl]

Please reopen the issue