MI

cloudyu_mixtral_7bx2_moe

MistralGGUF by TheBlokeUpdated 2023-12-23
Download on Hugging Face
Parameters12.9B
Context32K
Layers32
Architecturellama
Smallest quant4.4 GB
Quick answer

cloudyu_mixtral_7bx2_moe needs about 8.9 GB of memory at Q4_K_M (a 7.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 8 quants, from 4.4 GB (Q2_K) to 13.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

12.9B parameter Mixtral 7Bx2 MoE model in GGUF format

cloudyu_mixtral_7bx2_moe is a 12.9B parameter mixture of experts model based on Mistral architecture. It supports a 32768 token context window and is released under a cc‑by‑nc‑4.0 license. The model is available in several GGUF quantizations.

Good at

  • Large context handling
  • Mixture of experts architecture
  • Open source availability

Limits

  • No vision support
  • Requires GPU for optimal performance
  • License restricts commercial use

Best for

  • Long‑form text generation
  • Research prototyping
  • Educational demonstrations

Who it’s for. Developers and researchers who need a large‑context, open‑source LLM for experimentation. The model is suitable for non‑commercial projects and academic use.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.4 GB 5.9 GB
Fits Get file →
Q3_K_M5.7 GB 7.3 GB
Tight Get file →
Q4_07.3 GB 8.9 GB
Too big Get file →
Q4_K_M7.3 GB 8.9 GB
Too big Get file →
Q5_08.9 GB 10.4 GB
Too big Get file →
Q5_K_M8.9 GB 10.5 GB
Too big Get file →
Q6_K10.6 GB 12.1 GB
Too big Get file →
Q8_013.7 GB 15.3 GB
Too big Get file →

For 8 GB VRAM, Q2_K (4.36 GB, 5.9 GB memory) or Q3_K_M (5.68 GB, 7.3 GB memory) are suitable. With 12 GB VRAM, Q4_0 or Q4_K_M (7.28 GB, 8.9 GB memory) fit comfortably. For 16 GB VRAM, Q5_0 or Q5_K_M (8.87 GB, 10.4 GB memory) provide higher quality.

What GPU do you need for cloudyu_mixtral_7bx2_moe?

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: the best quant that fits is Q2_K (4.4 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q3_K_M (5.7 GB file, about 7.3 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_M (8.9 GB file, about 10.5 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (13.7 GB file, about 15.3 GB in use).

Which cloudyu_mixtral_7bx2_moe quant should you choose?

Q4_K_M is the usual starting point for cloudyu_mixtral_7bx2_moe: it balances file size and quality well. Here it is a 7.3 GB file.

The Q8_0 file is 13.7 GB, about 1.9 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 4.4 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

Architecturellama
Parameters12.9B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byTheBloke
FamilyMistral
Downloads (HF)1,498
Last updated2023-12-23

Frequently asked questions about cloudyu_mixtral_7bx2_moe

How much VRAM does cloudyu_mixtral_7bx2_moe need?

About 8.9 GB at Q4_K_M with an 8K context window. That is the 7.3 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_7bx2_moe on an 8 GB GPU?

Yes, with Q3_K_M: the 5.7 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of cloudyu_mixtral_7bx2_moe GGUF?

It depends on the quant: Q2_K is 4.4 GB, Q3_K_M is 5.7 GB, Q4_0 is 7.3 GB, Q4_K_M is 7.3 GB, Q5_0 is 8.9 GB, Q5_K_M is 8.9 GB and 2 more.

What context length does cloudyu_mixtral_7bx2_moe support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download cloudyu_mixtral_7bx2_moe GGUF?

The files are on Hugging Face in the TheBloke/Mixtral_7Bx2_MoE-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_7bx2_moe 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 cloudyu_mixtral_7bx2_moe on 8 GB VRAM?

Yes, using Q2_K or Q3_K_M quantizations will fit within 8 GB VRAM with approximate memory usage of 5.9 GB or 7.3 GB respectively.

Does this model support vision tasks?

No, the model has no vision capabilities.

Is the model suitable for commercial use?

No, the cc‑by‑nc‑4.0 license prohibits commercial use.

Other GGUFs of Mixtral_7Bx2_MoE

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Mistral models

All Mistral →

Other medium models

All medium models →