cloudyu_mixtral_34bx2_moe_60b needs about 36.9 GB of memory at Q4_K_M (a 34.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 7 quants, from 20.5 GB (Q2_K) to 49.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.
Mixtral 34Bx2 MoE 60B in GGUF format
cloudyu_mixtral_34bx2_moe_60b is a 60.8B parameter Mixture of Experts model based on the Mistral family. It is available in several GGUF quantisations and supports a 200000 token context window. The model is licensed under cc‑by‑nc‑4.0.
Good at
- Large context handling
- Mixture of Experts efficiency
- High parameter count
Limits
- No vision support
- Requires GPU for full performance
- License restricts commercial use
Best for
- Research on large language models
- Complex conversational AI
- Long‑form content generation
Who it’s for. Developers and researchers needing a large, context‑rich language model for non‑commercial projects. The model is suitable for local deployment with compatible GGUF tools.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 20.5 GB | 23.1 GB | Too big | Get file → | |
| Q3_K_M | 26.8 GB | 29.3 GB | Too big | Get file → | |
| Q4_0 | 34.3 GB | 36.8 GB | Too big | Get file → | |
| Q4_K_M | 34.4 GB | 36.9 GB | Too big | Get file → | |
| Q5_0 | 41.9 GB | 44.4 GB | Too big | Get file → | |
| Q5_K_M | 41.9 GB | 44.4 GB | Too big | Get file → | |
| Q6_K | 49.9 GB | 52.4 GB | Too big | Get file → |
For 8 GB VRAM use Q2_K (20.55 GB file, ~23.1 GB memory). For 12 GB VRAM use Q3_K_M (26.79 GB file, ~29.3 GB memory). For 16 GB VRAM use Q4_K_M (34.39 GB file, ~36.9 GB memory).
What GPU do you need for cloudyu_mixtral_34bx2_moe_60b?
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: the best quant that fits is Q2_K (20.5 GB file, about 23.1 GB in use).
- 32 GB VRAM: the best quant that fits is Q3_K_M (26.8 GB file, about 29.3 GB in use).
- 48 GB VRAM: the best quant that fits is Q5_K_M (41.9 GB file, about 44.4 GB in use).
Which cloudyu_mixtral_34bx2_moe_60b quant should you choose?
Q4_K_M is the usual starting point for cloudyu_mixtral_34bx2_moe_60b: it balances file size and quality well. Here it is a 34.4 GB file.
If memory is tight, the smallest file is Q2_K at 20.5 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about cloudyu_mixtral_34bx2_moe_60b
How much VRAM does cloudyu_mixtral_34bx2_moe_60b need?
About 36.9 GB at Q4_K_M with an 8K context window. That is the 34.4 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 cloudyu_mixtral_34bx2_moe_60b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 23.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of cloudyu_mixtral_34bx2_moe_60b GGUF?
It depends on the quant: Q2_K is 20.5 GB, Q3_K_M is 26.8 GB, Q4_0 is 34.3 GB, Q4_K_M is 34.4 GB, Q5_0 is 41.9 GB, Q5_K_M is 41.9 GB and 1 more.
What context length does cloudyu_mixtral_34bx2_moe_60b 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 cloudyu_mixtral_34bx2_moe_60b GGUF?
The files are on Hugging Face in the TheBloke/Mixtral_34Bx2_MoE_60B-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 cloudyu_mixtral_34bx2_moe_60b use?
Hugging Face lists the license as cc-by-nc-4.0. 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 this model on 8 GB VRAM?
Yes, using the Q2_K quantisation which requires about 23.1 GB of VRAM at 8 k context.
Does this model support vision tasks?
No, the model has no vision capabilities.
Is the model free to use commercially?
No, it is licensed under cc‑by‑nc‑4.0, which prohibits commercial use.