{"v":1,"id":"model:hf:Qwen/Qwen2.5-Coder-7B-Instruct-GGUF","slug":"model-qwen-qwen2-5-coder-7b-instruct-gguf","kind":"model","category":"llm","title":"Qwen2.5-Coder-7B-Instruct-GGUF","summary":"Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). As of now, Qwen2.5-Coder has covered six mainstream model sizes, 0.5, 1.5, 3, 7, 14, 32 bi…","source":{"provider":"hf","ref":"Qwen/Qwen2.5-Coder-7B-Instruct-GGUF","url":"https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct-GGUF","rev":"13fb94bfda8c8cf22497dc57b78f391a9acb426a","fetchedAt":"2026-10-02T20:53:57.151Z","etag":"W/\"2dc5-q3rUYwRUv/XAamhXvniVqpn2pHQ\""},"author":{"name":"Qwen","url":"https://huggingface.co/Qwen"},"license":{"spdx":"apache-2.0","raw":"apache-2.0","url":"https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct-GGUF/blob/main/LICENSE","open":true},"metrics":{"downloads":317229,"downloadsWeek":327838,"likes":505,"stars":27665,"openIssues":68,"pushedAt":"2026-01-09T03:05:47Z","takenAt":"2026-10-02T20:53:57.151Z"},"tags":["transformers","gguf","code","codeqwen","chat","qwen","qwen-coder","text-generation","en","endpoints_compatible","conversational"],"pipeline":"text-generation","links":{"github":"QwenLM/Qwen3","npm":"node-llama-cpp"},"updatedAt":"2024-11-12T07:59:32.000Z","collectedAt":"2026-10-02T20:53:57.151Z","review":{"numbers":["317,229 downloads on Hugging Face","505 likes","license apache-2.0","4.4 GB for qwen2.5-coder-7b-instruct-q4_k_m.gguf","27,665 stars on QwenLM/Qwen3","68 open issues and PRs","327,838 npm downloads a week for node-llama-cpp","latest node-llama-cpp@3.22.1"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T20:53:57.151Z","http":200},"description":"# Qwen2.5-Coder-7B-Instruct-GGUF\n\n## Introduction\n\nQwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). As of now, Qwen2.5-Coder has covered six mainstream model sizes, 0.5, 1.5, 3, 7, 14, 32 billion parameters, to meet the needs of different developers. Qwen2.5-Coder brings the following improvements upon CodeQwen1.5:\n\n- Significantly improvements in **code generation**, **code reasoning** and **code fixing**. Base on the strong Qwen2.5, we scale up the training tokens into 5.5 trillion including source code, text-code grounding, Synthetic data, etc. Qwen2.5-Coder-32B has become the current state-of-the-art open-source codeLLM, with its coding abilities matching those of GPT-4o.\n- A more comprehensive foundation for real-world applications such as **Code Agents**. Not only enhancing coding capabilities but also maintaining its strengths in mathematics and general competencies.\n- **Long-context Support** up to 128K tokens.\n\n**This repo contains the instruction-tuned 7B Qwen2.5-Coder model in the GGUF Format**, which has the following features:\n- Type: Causal Language Models\n- Training Stage: Pretraining & Post-training\n- Architecture: transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias\n- Number of Parameters: 7.61B\n- Number of Paramaters (Non-Embedding): 6.53B\n- Number of Layers: 28\n- Number of Attention Heads (GQA): 28 for Q and 4 for KV\n- Context Length: Full 32,768 tokens\n  - Note: Currently, only vLLM supports YARN for length extrapolating. If you want to process sequences up to 131,072 tokens, please refer to non-GGUF models.\n- Quantization: q2_K, q3_K_M, q4_0, q4_K_M, q5_0, q5_K_M, q6_K, q8_0\n\nFor more details, please refer to our [blog](https://qwenlm.github.io/blog/qwen2.5-coder-family/), [GitHub](https://github.com/QwenLM/Qwen2.5-Coder), [Documentation](https://qwen.readthedocs.io/en/latest/), [Arxiv](https://arxiv.org/abs…\n\nSource: https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct-GGUF","install":{"kind":"model","hfId":"Qwen/Qwen2.5-Coder-7B-Instruct-GGUF","gated":false,"format":"gguf","files":[{"name":"qwen2.5-coder-7b-instruct-fp16-00001-of-00004.gguf","size":3951521376,"sha256":"2da8da61187a860415e9a269a62320b220d66ac01b9afa720ffebc85c2f54f48"},{"name":"qwen2.5-coder-7b-instruct-fp16-00002-of-00004.gguf","size":3864909312,"sha256":"53c6599c57aadfb5bd1ea2f80b1119ba304424c675140c00cca91653aa9c9ba0"},{"name":"qwen2.5-coder-7b-instruct-fp16-00003-of-00004.gguf","size":3864894976,"sha256":"3128077b8774af24f0ee9d26668a95d9f3a305be8fb5c6d6cdcc314593ee0362"},{"name":"qwen2.5-coder-7b-instruct-fp16-00004-of-00004.gguf","size":3556527872,"sha256":"d52530f0a196e4447198d53212630540547860888ec552e62708c688d67eef71"},{"name":"qwen2.5-coder-7b-instruct-fp16.gguf","size":15237853184,"sha256":"688cb5d19a53f91843be63eacca134c3d7dfe9364c4263c67bbeb8c56bd16554"},{"name":"qwen2.5-coder-7b-instruct-q2_k.gguf","size":3015940032,"quant":"Q2_K","sha256":"6ce2630974b0ef631e2b29064cd10a9cb16b278d001961d72bfd86987392c8d9"},{"name":"qwen2.5-coder-7b-instruct-q3_k_m.gguf","size":3808391104,"quant":"Q3_K_M","sha256":"ff5c64615cf8a44651d208e9d8da1f753feefc21605e6c1ee67957aa77257c3c"},{"name":"qwen2.5-coder-7b-instruct-q4_0-00001-of-00002.gguf","size":3983228352,"quant":"Q4_0","sha256":"83eeb8e4e886fd9efb7587025c304a5bd382e3a60385038a206964d74a49d9f9"},{"name":"qwen2.5-coder-7b-instruct-q4_0-00002-of-00002.gguf","size":448162496,"quant":"Q4_0","sha256":"9dd22ece81c22beb5e578db7e4d3e1dd41172a057361736cf3c2295f61c8960c"},{"name":"qwen2.5-coder-7b-instruct-q4_0.gguf","size":4431390720,"quant":"Q4_0","sha256":"8561411b4705cbf2d105cf8e2084c6d6f1bcaba415249ce65fc5f21230d4961b"},{"name":"qwen2.5-coder-7b-instruct-q4_k_m-00001-of-00002.gguf","size":3993201376,"quant":"Q4_K_M","sha256":"89f120544682078148c5a86117de9af3a65c339111262f2d3ff01d80d48b14be"},{"name":"qwen2.5-coder-7b-instruct-q4_k_m-00002-of-00002.gguf","size":689872288,"quant":"Q4_K_M","sha256":"0183b3c850cfa96c31082c3af0123115300d3f62798c4448fa8f57bd0eac05e0"},{"name":"qwen2.5-coder-7b-instruct-q4_k_m.gguf","size":4683073536,"quant":"Q4_K_M","sha256":"509287f78cb4d4cf6b3843734733b914b2c158e43e22a7f4bf5e963800894d3c"},{"name":"qwen2.5-coder-7b-instruct-q5_0-00001-of-00002.gguf","size":4001112160,"quant":"Q5_0","sha256":"19658ae18ef0bbfbe06f6ba9ddfd177e84cd3016122459c5f0960765fa9fce71"},{"name":"qwen2.5-coder-7b-instruct-q5_0-00002-of-00002.gguf","size":1314064416,"quant":"Q5_0","sha256":"1b22dcf0e166a975a0b5b2da2bb9eb1c6dab03087b537b4fe309d075f3bfc742"},{"name":"qwen2.5-coder-7b-instruct-q5_k_m-00001-of-00002.gguf","size":3989841792,"quant":"Q5_K_M","sha256":"c605613a68d9e02d22d411f6304134457352a4d1e4dfdcaf8f2f25203901c03f"},{"name":"qwen2.5-coder-7b-instruct-q5_k_m-00002-of-00002.gguf","size":1454989568,"quant":"Q5_K_M","sha256":"e268483babb39a48cb1380b5b43e2d7ec202ebac2775efcfbaac939d9218f6ff"},{"name":"qwen2.5-coder-7b-instruct-q5_k_m.gguf","size":5444831232,"quant":"Q5_K_M","sha256":"586844eac4d6d6321689f0192c8aa8e69cd8625974a5cc2d925b1a03366e4d16"},{"name":"qwen2.5-coder-7b-instruct-q6_k-00001-of-00002.gguf","size":3950642496,"quant":"Q6_K","sha256":"6b99ee26f4b1f887b25dbb45491ec158391ba7ba73dbc4c75ca9560d3da4493a"},{"name":"qwen2.5-coder-7b-instruct-q6_k-00002-of-00002.gguf","size":2303556416,"quant":"Q6_K","sha256":"5103917f06a316394b6766b69217c7af101dbb3c53f5a84a2a4c1747b53c5109"},{"name":"qwen2.5-coder-7b-instruct-q6_k.gguf","size":6254198784,"quant":"Q6_K","sha256":"46291ddea1bfb608fe63d9a1907eea6918bda87a7626593edc4bf97c5fd73f9d"},{"name":"qwen2.5-coder-7b-instruct-q8_0-00001-of-00003.gguf","size":3980069280,"quant":"Q8_0","sha256":"e2fc5918a2b579d8e03a3752ad74dd191bc0f43204c90a29070f273f5283fee1"},{"name":"qwen2.5-coder-7b-instruct-q8_0-00002-of-00003.gguf","size":3942935680,"quant":"Q8_0","sha256":"912b7876d43dc19bbcf09368f4472f6cfea3458067a5bcaa660a68a9958276db"},{"name":"qwen2.5-coder-7b-instruct-q8_0-00003-of-00003.gguf","size":175520480,"quant":"Q8_0","sha256":"478f6a6b37072eeda02a98a59b6ef0b1a9131c9eae9a1181b6077f5e255fa6b2"},{"name":"qwen2.5-coder-7b-instruct-q8_0.gguf","size":8098525184,"quant":"Q8_0","sha256":"b36a4e1c3ddf2ba6fd5501b926128e5fc6430881caaff07e9629bd18f06f685f"}],"totalBytes":100439254112,"suggestedFile":"qwen2.5-coder-7b-instruct-q4_k_m.gguf","requirements":{"ramGb":6,"diskBytes":4683073536,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["llama.cpp","ollama"],"command":"lsh models install hf:Qwen/Qwen2.5-Coder-7B-Instruct-GGUF"}}