MI

MixtralOrochi8x7B i1

MistralGGUF by mradermacherUpdated 2024-05-06
Download on Hugging Face
Parameters46.7B
Context32K
Layers32
Architecturellama
Smallest quant10.0 GB
Quick answer

MixtralOrochi8x7B i1 needs about 30.2 GB of memory at Q4_K_M (a 28.6 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 19 quants, from 10.0 GB (IQ1_S) to 38.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

MixtralOrochi8x7B i1 – a 46.7B parameter Mixture of Experts model in GGUF format

MixtralOrochi8x7B i1 is a 46.7B parameter model based on the Mixtral architecture. It is a Mixture of Experts model with a trained context of 32768 tokens. The model is released under a cc‑by‑nc‑4.0 license.

Good at

  • Large context handling
  • Mixture of Experts specialization
  • Uncensored content generation

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • cc‑by‑nc‑4.0 license restricts commercial use

Best for

  • Research on large context language models
  • Developing unrestricted dialogue systems
  • Testing Mixture of Experts behavior

Who it’s for. Researchers and developers who need a large, uncensored language model with a 32768 token context window. The model is suitable for experimentation and prototyping in non‑commercial settings.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S10.0 GB 11.6 GB
Too big Get file →
IQ2_XXS12.7 GB 14.3 GB
Too big Get file →
IQ2_XS14.1 GB 15.7 GB
Too big Get file →
IQ2_S14.3 GB 15.9 GB
Too big Get file →
IQ2_M15.7 GB 17.2 GB
Too big Get file →
Q2_K17.5 GB 19.0 GB
Too big Get file →
IQ3_XXS18.4 GB 20.0 GB
Too big Get file →
IQ3_XS19.4 GB 21.0 GB
Too big Get file →
IQ3_S20.6 GB 22.2 GB
Too big Get file →
Q3_K_S20.6 GB 22.2 GB
Too big Get file →
IQ3_M21.6 GB 23.2 GB
Too big Get file →
Q3_K_M22.7 GB 24.3 GB
Too big Get file →
Q3_K_L24.3 GB 25.9 GB
Too big Get file →
IQ4_XS25.2 GB 26.8 GB
Too big Get file →
Q4_K_S26.9 GB 28.5 GB
Too big Get file →
Q4_K_M28.6 GB 30.2 GB
Too big Get file →
Q5_K_S32.4 GB 34.0 GB
Too big Get file →
Q5_K_M33.4 GB 35.0 GB
Too big Get file →
Q6_K38.5 GB 40.1 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (file size 9.99 GB, estimated 11.6 GB memory). For 12 GB VRAM, IQ2_XXS (12.73 GB, 14.3 GB memory). For 16 GB VRAM, IQ2_M (15.67 GB, 17.2 GB memory). Higher quants provide better quality at the cost of more memory.

What GPU do you need for MixtralOrochi8x7B i1?

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: the best quant that fits is IQ1_S (10.0 GB file, about 11.6 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ2_S (14.3 GB file, about 15.9 GB in use).
  • 24 GB VRAM: the best quant that fits is IQ3_M (21.6 GB file, about 23.2 GB in use).
  • 32 GB VRAM: the best quant that fits is Q4_K_M (28.6 GB file, about 30.2 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (38.5 GB file, about 40.1 GB in use).

Which MixtralOrochi8x7B i1 quant should you choose?

Q4_K_M is the usual starting point for MixtralOrochi8x7B i1: it balances file size and quality well. Here it is a 28.6 GB file.

If memory is tight, the smallest file is IQ1_S at 10.0 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
Parameters46.7B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyMistral
Downloads (HF)3,146
Last updated2024-05-06

Frequently asked questions about MixtralOrochi8x7B i1

How much VRAM does MixtralOrochi8x7B i1 need?

About 30.2 GB at Q4_K_M with an 8K context window. That is the 28.6 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 MixtralOrochi8x7B i1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of MixtralOrochi8x7B i1 GGUF?

It depends on the quant: IQ1_S is 10.0 GB, IQ2_XXS is 12.7 GB, IQ2_XS is 14.1 GB, IQ2_S is 14.3 GB, IQ2_M is 15.7 GB, Q2_K is 17.5 GB and 13 more.

What context length does MixtralOrochi8x7B i1 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 MixtralOrochi8x7B i1 GGUF?

The files are on Hugging Face in the mradermacher/MixtralOrochi8x7B-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 MixtralOrochi8x7B i1 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 MixtralOrochi8x7B i1 on 8 GB VRAM?

Use the IQ1_S quant; it requires about 11.6 GB of VRAM at 8k context, which is close to 8 GB but may need swapping.

Does MixtralOrochi8x7B i1 support vision tasks?

No, the model has no vision capabilities.

Is MixtralOrochi8x7B i1 suitable for commercial products?

The cc‑by‑nc‑4.0 license prohibits commercial use without permission.

Other GGUFs of MixtralOrochi8x7B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Mistral models

All Mistral →

Other large models

All large models →