60B MoE Coder v3 needs about 52.4 GB of memory at Q6_K (a 49.9 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.
60B MoE Coder v3 is a 60.8B-parameter Moe model in GGUF format, quantized by cloudyu. Its trained context length is 195K tokens. The repository has 1 quant file, from 49.9 GB (Q6_K) to 49.9 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q6_K | 49.9 GB | 52.4 GB | Too big | Get file → |
What GPU do you need for 60B MoE Coder v3?
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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Which 60B MoE Coder v3 quant should you choose?
Q6_K (49.9 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about 60B MoE Coder v3
How much VRAM does 60B MoE Coder v3 need?
About 52.4 GB at Q6_K with an 8K context window. That is the 49.9 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 60B MoE Coder v3 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 52.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of 60B MoE Coder v3 GGUF?
It depends on the quant: Q6_K is 49.9 GB.
What context length does 60B MoE Coder v3 support?
The GGUF header lists a trained context length of 200,000 tokens (195K). The KV cache grows with the context you use: about 2.0 GB at 8K and 8.1 GB at 32K.
Where can I download 60B MoE Coder v3 GGUF?
The files are on Hugging Face in the cloudyu/60B_MoE_Coder_v3_gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.