MI

models--v2ray--Mixtral-8x22B-v0.1

MistralGGUF by MaziyarPanahiUpdated 2024-04-15
Download on Hugging Face
Parameters141B
Context64K
Layers56
Architecturellama
Smallest quant29.6 GB
Quick answer

models--v2ray--Mixtral-8x22B-v0.1 needs about 88.0 GB of memory at Q4_K_M (a 85.6 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 15 quants, from 29.6 GB (IQ1_S) to 281.2 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.

Mixtral‑8x22B‑v0.1 – 141B MoE LLM with 65k token context

Mixtral‑8x22B‑v0.1 is a 141B parameter sparse Mixture of Experts model. It supports a context length of 65 k tokens and is released under Apache 2.0. The model is available in multiple GGUF quantizations for efficient deployment.

Good at

  • Large context handling
  • Sparse MoE efficiency
  • High parameter count

Limits

  • No vision support
  • Requires large VRAM for fp16
  • No moderation mechanisms

Best for

  • Long‑form content generation
  • Complex reasoning tasks
  • Research prototyping

Who it’s for. Developers and researchers needing a high‑capacity LLM with extended context. Suitable for environments with sufficient GPU memory and no need for vision or moderation features.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S29.6 GB 32.0 GB
Too big Get file →
IQ1_M32.7 GB 35.1 GB
Too big Get file →
Q2_K52.1 GB (5 parts) 54.5 GB
Too big Get file →
IQ3_XS58.2 GB (5 parts) 60.6 GB
Too big Get file →
Q3_K_S61.5 GB (5 parts) 63.9 GB
Too big Get file →
Q3_K_M67.8 GB (5 parts) 70.2 GB
Too big Get file →
Q3_K_L72.6 GB (5 parts) 75.0 GB
Too big Get file →
IQ4_XS76.4 GB (5 parts) 78.7 GB
Too big Get file →
Q4_K_S80.5 GB (5 parts) 82.9 GB
Too big Get file →
Q4_K_M85.6 GB (5 parts) 88.0 GB
Too big Get file →
Q5_K_S97.0 GB (5 parts) 99.4 GB
Too big Get file →
Q5_K_M100.0 GB (5 parts) 102.3 GB
Too big Get file →
Q6_K115.5 GB (5 parts) 117.9 GB
Too big Get file →
Q8_0149.4 GB (5 parts) 151.8 GB
Too big Get file →
—281.2 GB (7 parts) 283.6 GB
Too big Get file →

For 8 GB VRAM use Q4_K_S (80.48 GB file, ~82.9 GB memory at 8 k context). For 16 GB VRAM use Q3_K_M (67.79 GB file, ~70.2 GB memory). For 32 GB VRAM use Q2_K (52.1 GB file, ~54.5 GB memory).

What GPU do you need for models--v2ray--Mixtral-8x22B-v0.1?

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: the best quant that fits is IQ1_S (29.6 GB file, about 32.0 GB in use).
  • 48 GB VRAM: the best quant that fits is IQ1_M (32.7 GB file, about 35.1 GB in use).

Which models--v2ray--Mixtral-8x22B-v0.1 quant should you choose?

Q4_K_M is the usual starting point for models--v2ray--Mixtral-8x22B-v0.1: it balances file size and quality well. Here it is a 85.6 GB file.

The Q8_0 file is 149.4 GB, about 1.7 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 IQ1_S at 29.6 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
Parameters141B (approximate, mixture of experts)
Layers56
Trained context65,536 tokens
KV cache (fp16)224 KB per token

Source

Quantized byMaziyarPanahi
FamilyMistral
Licenseapache-2.0
Downloads (HF)50,817
Last updated2024-04-15

Frequently asked questions about models--v2ray--Mixtral-8x22B-v0.1

How much VRAM does models--v2ray--Mixtral-8x22B-v0.1 need?

About 88.0 GB at Q4_K_M with an 8K context window. That is the 85.6 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 models--v2ray--Mixtral-8x22B-v0.1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 32.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of models--v2ray--Mixtral-8x22B-v0.1 GGUF?

It depends on the quant: IQ1_S is 29.6 GB, IQ1_M is 32.7 GB, Q2_K is 52.1 GB, IQ3_XS is 58.2 GB, Q3_K_S is 61.5 GB, Q3_K_M is 67.8 GB and 9 more.

What context length does models--v2ray--Mixtral-8x22B-v0.1 support?

The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 1.9 GB at 8K and 7.5 GB at 32K.

Where can I download models--v2ray--Mixtral-8x22B-v0.1 GGUF?

The files are on Hugging Face in the MaziyarPanahi/Mixtral-8x22B-v0.1-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 models--v2ray--Mixtral-8x22B-v0.1 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 Mixtral‑8x22B‑v0.1 on 8 GB VRAM?

Only with a low‑precision quant like Q4_K_S, which still requires ~82.9 GB memory at 8 k context, so 8 GB VRAM is insufficient.

Does the model support image inputs?

No, the model has no vision capabilities.

What license applies to this model?

The model is licensed under Apache 2.0.

Similar models

Browse all →

More from MaziyarPanahi

All by MaziyarPanahi →

More Mistral models

All Mistral →

Other large models

All large models →