diff --git a/README.md b/README.md
index 2e8b6f281a..527c28bf30 100644
--- a/README.md
+++ b/README.md
@@ -150,8 +150,8 @@ Every model is written from scratch to maximize performance and remove layers of
 | Qwen2.5 Math | 1.5B, 7B, 72B | Alibaba Group | [An, Yang et al. 2024](https://arxiv.org/abs/2409.12122)                                          |
 | QwQ | 32B | Alibaba Group | [Qwen Team 2025](https://qwenlm.github.io/blog/qwq-32b/)                                                                         |
 | QwQ-Preview | 32B | Alibaba Group | [Qwen Team 2024](https://qwenlm.github.io/blog/qwq-32b-preview/)                                                                         |
-| Qwen3 | 0.6B, 1.7B, 4B{Hybrid, Thinking-2507}, 8B, 14B, 32B | Alibaba Group | [Qwen Team 2025](https://arxiv.org/abs/2505.09388/)                                                                         |
-| Qwen3 MoE | 30B{Hybrid, Thinking-2507}, 235B{Hybrid, Thinking-2507} | Alibaba Group | [Qwen Team 2025](https://arxiv.org/abs/2505.09388/)                                                                         |
+| Qwen3 | 0.6B, 1.7B, 4B{Hybrid, Thinking-2507, Instruct-2507}, 8B, 14B, 32B | Alibaba Group | [Qwen Team 2025](https://arxiv.org/abs/2505.09388/)                                                                         |
+| Qwen3 MoE | 30B{Hybrid, Thinking-2507, Instruct-2507}, 235B{Hybrid, Thinking-2507, Instruct-2507} | Alibaba Group | [Qwen Team 2025](https://arxiv.org/abs/2505.09388/)                                                                         |
 | R1 Distill Llama | 8B, 70B | DeepSeek AI | [DeepSeek AI 2025](https://github.com/deepseek-ai/DeepSeek-R1/blob/main/DeepSeek_R1.pdf)                                                                                 |
 | SmolLM2 | 135M, 360M, 1.7B | Hugging Face | [Hugging Face 2024](https://github.com/huggingface/smollm)                                                               |
 | Salamandra | 2B, 7B | Barcelona Supercomputing Centre | [BSC-LTC 2024](https://github.com/BSC-LTC/salamandra)                                                                         |
diff --git a/litgpt/config.py b/litgpt/config.py
index 062653f940..63ee4c9ee1 100644
--- a/litgpt/config.py
+++ b/litgpt/config.py
@@ -2859,11 +2859,11 @@ def norm_class(self) -> Type:
 ]
 configs.extend(qwen_3_moe)
 
-qwen_3_2507_thinking = [
+qwen_3_2507_thinking_instruct = [
     # https://huggingface.co/Qwen/Qwen3-235B-A22B-Thinking-2507/blob/main/config.json
     dict(
-        name="Qwen3-235B-A22B-Thinking-2507",
-        hf_config=dict(org="Qwen", name="Qwen3-235B-A22B-Thinking-2507"),
+        name="Qwen3-235B-A22B-{}-2507",
+        hf_config=dict(org="Qwen", name="Qwen3-235B-A22B-{}-2507"),
         block_size=262144,
         head_size=128,
         vocab_size=151643,
@@ -2887,8 +2887,8 @@ def norm_class(self) -> Type:
     ),
     # https://huggingface.co/Qwen/Qwen3-30B-A3B-Thinking-2507/blob/main/config.json
     dict(
-        name="Qwen3-30B-A3B-Thinking-2507",
-        hf_config=dict(org="Qwen", name="Qwen3-30B-A3B-Thinking-2507"),
+        name="Qwen3-30B-A3B-{}-2507",
+        hf_config=dict(org="Qwen", name="Qwen3-30B-A3B-{}-2507"),
         block_size=262144,
         head_size=128,
         vocab_size=151643,
@@ -2912,8 +2912,8 @@ def norm_class(self) -> Type:
     ),
     # https://huggingface.co/Qwen/Qwen3-4B-Thinking-2507/blob/main/config.json
     dict(
-        name="Qwen3-4B-Thinking-2507",
-        hf_config=dict(org="Qwen", name="Qwen3-4B-Thinking-2507"),
+        name="Qwen3-4B-{}-2507",
+        hf_config=dict(org="Qwen", name="Qwen3-4B-{}-2507"),
         block_size=262144,
         vocab_size=151643,
         padded_vocab_size=151936,
@@ -2933,7 +2933,13 @@ def norm_class(self) -> Type:
         norm_qk=True,
     ),
 ]
-configs.extend(qwen_3_2507_thinking)
+
+for c in qwen_3_2507_thinking_instruct:
+    for kind in ("Thinking", "Instruct"):
+        copy = deepcopy(c)
+        copy["name"] = c["name"].format(kind)
+        copy["hf_config"]["name"] = c["hf_config"]["name"].format(kind)
+        configs.append(copy)
 
 #############
 # Salamandra
diff --git a/tests/test_model.py b/tests/test_model.py
index b6cf94a0ef..a3677d21af 100644
--- a/tests/test_model.py
+++ b/tests/test_model.py
@@ -1083,7 +1083,16 @@ def test_against_original_qwen_2_5(model_name, device, dtype):
 
 @torch.inference_mode()
 @pytest.mark.parametrize(
-    "model_name", ["Qwen3-0.6B", "Qwen3-8B", "Qwen3-4B-Base", "Qwen3-14B-Base", "Qwen3-32B", "Qwen3-4B-Thinking-2507"]
+    "model_name",
+    [
+        "Qwen3-0.6B",
+        "Qwen3-8B",
+        "Qwen3-4B-Base",
+        "Qwen3-14B-Base",
+        "Qwen3-32B",
+        "Qwen3-4B-Thinking-2507",
+        "Qwen3-4B-Instruct-2507",
+    ],
 )
 @pytest.mark.parametrize(
     ("device", "dtype"),
@@ -1143,7 +1152,9 @@ def test_against_original_qwen_3(model_name, device, dtype):
 
 
 @torch.inference_mode()
-@pytest.mark.parametrize("model_name", ["Qwen3-30B-A3B", "Qwen3-235B-A22B", "Qwen3-235B-A22B-Thinking-2507"])
+@pytest.mark.parametrize(
+    "model_name", ["Qwen3-30B-A3B", "Qwen3-235B-A22B", "Qwen3-235B-A22B-Thinking-2507", "Qwen3-235B-A22B-Instruct-2507"]
+)
 @pytest.mark.parametrize(
     ("device", "dtype"),
     [
diff --git a/tutorials/download_model_weights.md b/tutorials/download_model_weights.md
index 25b34acdd2..fcd3111ea6 100644
--- a/tutorials/download_model_weights.md
+++ b/tutorials/download_model_weights.md
@@ -48,8 +48,8 @@ LitGPT supports a variety of LLM architectures with publicly available weights.
 | Qwen2.5 Math | 1.5B, 7B, 72B | Alibaba Group | [An, Yang et al. 2024](https://arxiv.org/abs/2409.12122)                                          |
 | QwQ | 32B | Alibaba Group | [Qwen Team 2025](https://qwenlm.github.io/blog/qwq-32b/)                                                                         |
 | QwQ-Preview | 32B | Alibaba Group | [Qwen Team 2024](https://qwenlm.github.io/blog/qwq-32b-preview/)                                                                         |
-| Qwen3 | 0.6B, 1.7B, 4B{Hybrid, Thinking-2507}, 8B, 14B, 32B | Alibaba Group | [Qwen Team 2025](https://arxiv.org/abs/2505.09388/)                                                                         |
-| Qwen3 MoE | 30B{Hybrid, Thinking-2507}, 235B{Hybrid, Thinking-2507} | Alibaba Group | [Qwen Team 2025](https://arxiv.org/abs/2505.09388/)                                                                         |
+| Qwen3 | 0.6B, 1.7B, 4B{Hybrid, Thinking-2507, Instruct-2507}, 8B, 14B, 32B | Alibaba Group | [Qwen Team 2025](https://arxiv.org/abs/2505.09388/)                                                                         |
+| Qwen3 MoE | 30B{Hybrid, Thinking-2507, Instruct-2507}, 235B{Hybrid, Thinking-2507, Instruct-2507} | Alibaba Group | [Qwen Team 2025](https://arxiv.org/abs/2505.09388/)                                                                         |
 | R1 Distll Llama | 8B, 70B | DeepSeek AI | [DeepSeek AI 2025](https://github.com/deepseek-ai/DeepSeek-R1/blob/main/DeepSeek_R1.pdf)                                                                         |
 | RedPajama-INCITE | 3B, 7B | Together | [Together 2023](https://together.ai/blog/redpajama-models-v1)                                                                 |
 | SmolLM2 | 135M, 360M, 1.7B | Hugging Face | [Hugging Face 2024](https://github.com/huggingface/smollm)                                                               |
@@ -237,6 +237,26 @@ Qwen/Qwen2.5-Math-7B
 Qwen/Qwen2.5-Math-7B-Instruct
 Qwen/Qwen2.5-Math-72B
 Qwen/Qwen2.5-Math-72B-Instruct
+Qwen/Qwen3-0.6B
+Qwen/Qwen3-0.6B-Base
+Qwen/Qwen3-1.7B
+Qwen/Qwen3-1.7B-Base
+Qwen/Qwen3-4B
+Qwen/Qwen3-4B-Base
+Qwen/Qwen3-8B
+Qwen/Qwen3-8B-Base
+Qwen/Qwen3-14B
+Qwen/Qwen3-14B-Base
+Qwen/Qwen3-32B
+Qwen/Qwen3-30B-A3B
+Qwen/Qwen3-30B-A3B-Base
+Qwen/Qwen3-235B-A22B
+Qwen/Qwen3-4B-Thinking-2507
+Qwen/Qwen3-4B-Instruct-2507
+Qwen/Qwen3-30B-A3B-Thinking-2507
+Qwen/Qwen3-30B-A3B-Instruct-2507
+Qwen/Qwen3-235B-A22B-Thinking-2507
+Qwen/Qwen3-235B-A22B-Instruct-2507
 Qwen/QwQ-32B
 Qwen/QwQ-32B-Preview
 stabilityai/FreeWilly2