Qwen25 Coder 3b Claude needs about 2.7 GB of memory at Q4_K_M (a 1.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 1.2 GB.
Qwen2.5-Coder 3B distilled for fast local coding and reasoning
Qwen2.5-Coder 3B Claude is a 3.09 B parameter model fine‑tuned on Claude 4.6 Opus reasoning trajectories. It supports a full 32,768 token context and is optimized for local inference on consumer GPUs. The model is available in a Q4_K_M quantized GGUF file of 1.93 GB.
Good at
- Structured step‑by‑step reasoning
- Python and JavaScript code generation
- Multi‑step math and logic tasks
Limits
- Requires at least 4 GB VRAM for Q4_K_M
- No vision or audio capabilities
- Apache‑2.0 license restricts commercial redistribution
Best for
- Local code generation in IDEs
- Automated code review tools
- Educational coding assistants
Who it’s for. Developers and researchers who need a lightweight, private coding model that can run on a single GPU. The model is suitable for local inference without internet access and for building private code‑assistant applications.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 1.9 GB | 2.7 GB | Fits | Get file → |
The only available quant is Q4_K_M, 1.93 GB in size, which uses about 2.7 GB of VRAM at 8 k context. For 8 GB VRAM systems, this quant is well within limits. If more VRAM is available, higher‑precision quants are not provided in the file list.
What GPU do you need for Qwen25 Coder 3b Claude?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is Q4_K_M (1.9 GB file, about 2.7 GB in use).
Which Qwen25 Coder 3b Claude quant should you choose?
Q4_K_M is the usual starting point for Qwen25 Coder 3b Claude: it balances file size and quality well. Here it is a 1.9 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Qwen25 Coder 3b Claude
How much VRAM does Qwen25 Coder 3b Claude need?
About 2.7 GB at Q4_K_M with an 8K context window. That is the 1.9 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Qwen25 Coder 3b Claude on an 8 GB GPU?
Yes, with Q4_K_M: the 1.9 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qwen25 Coder 3b Claude GGUF?
It depends on the quant: Q4_K_M is 1.9 GB.
What context length does Qwen25 Coder 3b Claude support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.2 GB at 32K.
Where can I download Qwen25 Coder 3b Claude GGUF?
The files are on Hugging Face in the ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Qwen25 Coder 3b Claude use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Qwen2.5-Coder 3B on 4GB VRAM?
Yes, the Q4_K_M quantized model requires approximately 2.7 GB VRAM at 8 k context, fitting comfortably in 4 GB VRAM.
Does this model support image input?
No, the model has no vision capabilities and only processes text.
What license applies to this model?
The model is released under the Apache‑2.0 license, allowing free use with attribution.