Qwen3 Coder 64B needs about 40.4 GB of memory at Q4_K_M (a 39.1 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 24 quants, from 0.4 GB to 52.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.
Qwen3 Coder 64B – 64.3B parameter coding model
Qwen3 Coder 64B is a 64.3B parameter model from the Qwen family, pruned with Cerebras REAP to remove 20% of MoE experts. It supports coding and tool usage and is available in multiple GGUF quantizations.
Good at
- Coding tasks
- Tool integration
- Large context handling
Limits
- Requires large VRAM for higher quants
- No vision support
- License is apache-2.0
Best for
- Developing code assistants
- Automating coding workflows
- Large‑scale code generation
Who it’s for. Engineers and researchers needing a powerful coding LLM that can run locally with GGUF. The model is suitable for developers who can manage the memory requirements of the larger quantizations.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.4 GB | 1.7 GB | Fits | Get file → | |
| IQ1_S | 13.3 GB | 14.6 GB | Too big | Get file → | |
| IQ1_M | 14.8 GB | 16.1 GB | Too big | Get file → | |
| IQ2_XXS | 17.2 GB | 18.5 GB | Too big | Get file → | |
| IQ2_XS | 19.1 GB | 20.4 GB | Too big | Get file → | |
| IQ2_S | 19.3 GB | 20.6 GB | Too big | Get file → | |
| IQ2_M | 21.2 GB | 22.5 GB | Too big | Get file → | |
| Q2_K_S | 22.1 GB | 23.5 GB | Too big | Get file → | |
| Q2_K | 23.7 GB | 25.0 GB | Too big | Get file → | |
| IQ3_XXS | 25.0 GB | 26.3 GB | Too big | Get file → | |
| IQ3_XS | 26.5 GB | 27.8 GB | Too big | Get file → | |
| Q3_K_S | 27.9 GB | 29.2 GB | Too big | Get file → | |
| IQ3_S | 28.0 GB | 29.3 GB | Too big | Get file → | |
| IQ3_M | 28.3 GB | 29.6 GB | Too big | Get file → | |
| Q3_K_M | 30.9 GB | 32.2 GB | Too big | Get file → | |
| Q3_K_L | 33.4 GB | 34.7 GB | Too big | Get file → | |
| IQ4_XS | 34.5 GB | 35.8 GB | Too big | Get file → | |
| Q4_0 | 36.5 GB | 37.8 GB | Too big | Get file → | |
| Q4_K_S | 36.7 GB | 38.0 GB | Too big | Get file → | |
| Q4_K_M | 39.1 GB | 40.4 GB | Too big | Get file → | |
| Q4_1 | 40.4 GB | 41.7 GB | Too big | Get file → | |
| Q5_K_S | 44.4 GB | 45.7 GB | Too big | Get file → | |
| Q5_K_M | 45.8 GB | 47.1 GB | Too big | Get file → | |
| Q6_K | 52.9 GB | 54.2 GB | Too big | Get file → |
For 8 GB VRAM, use the IQ1_S quant (13.32 GB file, 14.6 GB memory at 8 k context). If 16 GB VRAM is available, IQ1_M (14.76 GB file, 16.1 GB memory) or Q2_XXS (17.16 GB file, 18.5 GB memory) are viable. Larger quants such as Q4_K_M require more than 32 GB VRAM.
What GPU do you need for Qwen3 Coder 64B?
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 the main file (0.4 GB file, about 1.7 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.7 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.7 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.4 GB file, about 1.7 GB in use).
- 16 GB VRAM: the best quant that fits is IQ1_S (13.3 GB file, about 14.6 GB in use).
- 24 GB VRAM: the best quant that fits is Q2_K_S (22.1 GB file, about 23.5 GB in use).
- 32 GB VRAM: the best quant that fits is IQ3_M (28.3 GB file, about 29.6 GB in use).
- 48 GB VRAM: the best quant that fits is Q5_K_M (45.8 GB file, about 47.1 GB in use).
Which Qwen3 Coder 64B quant should you choose?
Q4_K_M is the usual starting point for Qwen3 Coder 64B: it balances file size and quality well. Here it is a 39.1 GB file.
If memory is tight, the smallest file is the first one in the table at 0.4 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Qwen3 Coder 64B
How much VRAM does Qwen3 Coder 64B need?
About 40.4 GB at Q4_K_M with an 8K context window. That is the 39.1 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 Qwen3 Coder 64B on an 8 GB GPU?
Yes, with the smaller files: the 0.4 GB file needs about 1.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qwen3 Coder 64B GGUF?
It depends on the quant: file is 0.4 GB, IQ1_S is 13.3 GB, IQ1_M is 14.8 GB, IQ2_XXS is 17.2 GB, IQ2_XS is 19.1 GB, IQ2_S is 19.3 GB and 18 more.
What context length does Qwen3 Coder 64B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.
Where can I download Qwen3 Coder 64B GGUF?
The files are on Hugging Face in the mradermacher/Qwen3-Coder-64B-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Qwen3 Coder 64B 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 Qwen3 Coder 64B on 8 GB VRAM?
Only the IQ1_S quant (13.32 GB file, 14.6 GB memory at 8 k context) is close to that limit; it may still exceed 8 GB VRAM when running.
Does this model support vision?
No, the model does not have vision capabilities.
What license applies to this model?
The model is released under the apache-2.0 license.