MI

Mixtral 8x22B v0.1 iMat

MistralGGUF by InferenceIllusionistUpdated 2024-04-24
Download on Hugging Face
Parameters141B
Context32K
Layers56
Architecturellama
Smallest quant29.6 GB
Quick answer

Mixtral 8x22B v0.1 iMat 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 18 quants, from 29.6 GB (IQ1_S) to 149.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.

Mixtral 8x22B v0.1 iMat – a 141 B parameter Mistral family model

Mixtral 8x22B v0.1 iMat is a 141 B parameter mixture of experts model based on the Mistral architecture. It supports a 32768 token context window and is available in multiple GGUF quantizations.

Good at

  • Large context handling
  • High parameter count
  • Mixture of experts architecture

Limits

  • No license information provided
  • No vision or audio support
  • Requires large VRAM for higher quants

Best for

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

Who it’s for. Developers and researchers needing a large, context‑rich language model for text‑only workloads. Suitable for environments with sufficient GPU memory to run the desired quantization.

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 →
IQ2_XXS37.9 GB 40.3 GB
Too big Get file →
IQ2_XS42.0 GB 44.4 GB
Too big Get file →
IQ2_S42.6 GB 45.0 GB
Too big Get file →
IQ2_M46.7 GB 49.1 GB
Too big Get file →
Q2_K52.1 GB (3 parts) 54.5 GB
Too big Get file →
IQ3_XXS54.9 GB (3 parts) 57.3 GB
Too big Get file →
IQ3_XS58.2 GB (3 parts) 60.6 GB
Too big Get file →
IQ3_S61.5 GB (3 parts) 63.9 GB
Too big Get file →
IQ3_M64.5 GB (4 parts) 66.9 GB
Too big Get file →
Q3_K_M67.8 GB (4 parts) 70.2 GB
Too big Get file →
Q4_K_S80.5 GB (4 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) 102.4 GB
Too big Get file →
Q6_K115.5 GB (6 parts) 117.9 GB
Too big Get file →
Q8_0149.4 GB (8 parts) 151.8 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (32 GB memory estimate) or IQ1_M (35.1 GB). For 16 GB VRAM, IQ2_XXS (40.3 GB) or IQ2_XS (44.4 GB) are appropriate. For 24 GB VRAM, IQ2_S (45 GB) or IQ2_M (49.1 GB) fit within the budget. Higher quants require proportionally more memory.

What GPU do you need for Mixtral 8x22B v0.1 iMat?

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 IQ2_S (42.6 GB file, about 45.0 GB in use).

Which Mixtral 8x22B v0.1 iMat quant should you choose?

Q4_K_M is the usual starting point for Mixtral 8x22B v0.1 iMat: 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 context32,768 tokens
KV cache (fp16)224 KB per token

Source

FamilyMistral
Downloads (HF)1,370
Last updated2024-04-24

Frequently asked questions about Mixtral 8x22B v0.1 iMat

How much VRAM does Mixtral 8x22B v0.1 iMat 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 Mixtral 8x22B v0.1 iMat 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 Mixtral 8x22B v0.1 iMat GGUF?

It depends on the quant: IQ1_S is 29.6 GB, IQ1_M is 32.7 GB, IQ2_XXS is 37.9 GB, IQ2_XS is 42.0 GB, IQ2_S is 42.6 GB, IQ2_M is 46.7 GB and 12 more.

What context length does Mixtral 8x22B v0.1 iMat support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.9 GB at 8K and 7.5 GB at 32K.

Where can I download Mixtral 8x22B v0.1 iMat GGUF?

The files are on Hugging Face in the InferenceIllusionist/Mixtral-8x22B-v0.1-iMat-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Mixtral 8x22B v0.1 iMat on 8 GB VRAM?

No, the smallest quant requires at least 32 GB memory at 8k context. You would need a larger GPU.

Does this model support image generation?

No, the model is text‑only and does not include vision capabilities.

Are the quantizations verified?

All quants are verified working prior to uploading to the repo.

Similar models

Browse all →

More from InferenceIllusionist

All by InferenceIllusionist →

More Mistral models

All Mistral →

Other large models

All large models →