{"v":1,"id":"model:hf:Qwen/Qwen3-0.6B-GGUF","slug":"model-qwen-qwen3-0-6b-gguf","kind":"model","category":"llm","title":"Qwen3-0.6B-GGUF","summary":"Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers grou…","source":{"provider":"hf","ref":"Qwen/Qwen3-0.6B-GGUF","url":"https://huggingface.co/Qwen/Qwen3-0.6B-GGUF","rev":"23749fefcc72300e3a2ad315e1317431b06b590a","fetchedAt":"2026-10-02T20:53:53.111Z","etag":"W/\"18d9-BUbRQqLb7WQ5pw67CMkQAy29bXw\""},"author":{"name":"Qwen","url":"https://huggingface.co/Qwen"},"license":{"spdx":"apache-2.0","raw":"apache-2.0","url":"https://huggingface.co/Qwen/Qwen3-0.6B-GGUF/blob/main/LICENSE","open":true},"metrics":{"downloads":345227,"downloadsWeek":327838,"likes":88,"stars":27665,"openIssues":68,"pushedAt":"2026-01-09T03:05:47Z","takenAt":"2026-10-02T20:53:53.111Z"},"tags":["gguf","text-generation","endpoints_compatible","conversational"],"pipeline":"text-generation","links":{"github":"QwenLM/Qwen3","npm":"node-llama-cpp"},"updatedAt":"2025-05-09T07:15:43.000Z","collectedAt":"2026-10-02T20:53:53.111Z","review":{"numbers":["345,227 downloads on Hugging Face","88 likes","license apache-2.0","0.6 GB for Qwen3-0.6B-Q8_0.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":"2026-10-02T20:53:53.111Z","http":200},"description":"# Qwen3-0.6B-GGUF\n\n    \n\n## Qwen3 Highlights\n\nQwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features:\n\n- **Uniquely support of seamless switching between thinking mode** (for complex logical reasoning, math, and coding) and **non-thinking mode** (for efficient, general-purpose dialogue) **within single model**, ensuring optimal performance across various scenarios.\n- **Significantly enhancement in its reasoning capabilities**, surpassing previous QwQ (in thinking mode) and Qwen2.5 instruct models (in non-thinking mode) on mathematics, code generation, and commonsense logical reasoning.\n- **Superior human preference alignment**, excelling in creative writing, role-playing, multi-turn dialogues, and instruction following, to deliver a more natural, engaging, and immersive conversational experience.\n- **Expertise in agent capabilities**, enabling precise integration with external tools in both thinking and unthinking modes and achieving leading performance among open-source models in complex agent-based tasks.\n- **Support of 100+ languages and dialects** with strong capabilities for **multilingual instruction following** and **translation**.\n\n## Model Overview\n\n**Qwen3-0.6B** has the following features:\n- Type: Causal Language Models\n- Training Stage: Pretraining & Post-training\n- Number of Parameters: 0.6B\n- Number of Paramaters (Non-Embedding): 0.44B\n- Number of Layers: 28\n- Number of Attention Heads (GQA): 16 for Q and 8 for KV\n\n- Context Length: 32,768.\n- Quantization: q8_0\n\nFor more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our [blog](https://qwenlm.github.io/blog/qwen3…\n\nSource: https://huggingface.co/Qwen/Qwen3-0.6B-GGUF","install":{"kind":"model","hfId":"Qwen/Qwen3-0.6B-GGUF","gated":false,"format":"gguf","files":[{"name":"Qwen3-0.6B-Q8_0.gguf","size":639446688,"quant":"Q8_0","sha256":"9465e63a22add5354d9bb4b99e90117043c7124007664907259bd16d043bb031"}],"totalBytes":639446688,"suggestedFile":"Qwen3-0.6B-Q8_0.gguf","requirements":{"ramGb":2,"diskBytes":639446688,"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/Qwen3-0.6B-GGUF"}}