MI

Mixtral-8x22B-Capyboros-v1

MistralGGUF by mradermacherUpdated 2024-05-19
Download on Hugging Face
Parameters141B
Context64K
Layers56
Architecturellama
Smallest quant29.6 GB
Quick answer

Mixtral-8x22B-Capyboros-v1 needs about 40.3 GB of memory at IQ2_XXS (a 37.9 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 6 quants, from 29.6 GB (IQ1_S) to 46.7 GB (IQ2_M). Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.

Mixtral-8x22B-Capyboros-v1 – a 141B parameter Mistral model fine‑tuned with QLoRA

Mixtral-8x22B-Capyboros-v1 is a 141B parameter Mistral model fine‑tuned with QLoRA on the Capybara and Airoboros datasets. It supports up to 65536 context tokens and is released under the Apache‑2.0 license.

Good at

  • Large context reasoning
  • Instruct‑style dialogue
  • Fine‑tuned on diverse datasets

Limits

  • Requires high VRAM for full precision
  • No vision support
  • No explicit language list

Best for

  • Research prototypes
  • Enterprise chatbots
  • Long‑form content generation

Who it’s for. Engineers and researchers needing a large, instruction‑tuned LLM with extensive context. The model is suitable for developers who can manage the memory demands of a 141B parameter model.

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 →

For 8 GB VRAM, use IQ1_S (file size 29.65 GB, estimated 32 GB memory at 8 k context). For 16 GB VRAM, IQ1_M (32.74 GB, 35.1 GB memory) is appropriate. For 24 GB VRAM, IQ2_XXS (37.89 GB, 40.3 GB memory) provides a balance between size and performance.

What GPU do you need for Mixtral-8x22B-Capyboros-v1?

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-Capyboros-v1 quant should you choose?

IQ2_XXS (37.9 GB) is the middle option in this repository. 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.

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 bymradermacher
FamilyMistral
Licenseapache-2.0
Downloads (HF)595
Last updated2024-05-19

Frequently asked questions about Mixtral-8x22B-Capyboros-v1

How much VRAM does Mixtral-8x22B-Capyboros-v1 need?

About 40.3 GB at IQ2_XXS with an 8K context window. That is the 37.9 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 Mixtral-8x22B-Capyboros-v1 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-Capyboros-v1 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.

What context length does Mixtral-8x22B-Capyboros-v1 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 Mixtral-8x22B-Capyboros-v1 GGUF?

The files are on Hugging Face in the mradermacher/Mixtral-8x22B-Capyboros-v1-i1-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 Mixtral-8x22B-Capyboros-v1 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-Capyboros-v1 on 8 GB VRAM?

Use the IQ1_S quant, which requires approximately 32 GB of VRAM at 8 k context.

What context length does this model support?

The model was trained with 65536 context tokens and supports up to that length.

Is this model licensed for commercial use?

Yes, it is released under the Apache‑2.0 license, which allows commercial use.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Mistral models

All Mistral →

Other large models

All large models →