MI

Air Striker Mixtral 8x7B Instruct ZLoss

MistralGGUF by LoneStrikerUpdated 2024-01-27
Download on Hugging Face
Parameters46.7B
Context32K
Layers32
Architecturellama
Smallest quant12.3 GB
Quick answer

Air Striker Mixtral 8x7B Instruct ZLoss needs about 30.0 GB of memory at Q4_K_M (a 28.4 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 11 quants, from 12.3 GB (IQ2_XXS) to 38.4 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Air Striker Mixtral 8x7B Instruct ZLoss is a 46.7B-parameter Mistral model in GGUF format, quantized by LoneStriker. Its trained context length is 32K tokens. The repository has 11 quant files, from 12.3 GB (IQ2_XXS) to 38.4 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS12.3 GB 13.9 GB
Too big Get file →
IQ2_XS13.7 GB 15.2 GB
Too big Get file →
Q2_K17.3 GB 18.9 GB
Too big Get file →
Q3_K_S20.4 GB 22.0 GB
Too big Get file →
Q3_K_M22.5 GB 24.1 GB
Too big Get file →
Q3_K_L24.2 GB 25.7 GB
Too big Get file →
Q4_K_S26.7 GB 28.3 GB
Too big Get file →
Q4_K_M28.4 GB 30.0 GB
Too big Get file →
Q5_K_S32.2 GB 33.8 GB
Too big Get file →
Q5_K_M33.2 GB 34.8 GB
Too big Get file →
Q6_K38.4 GB 40.0 GB
Too big Get file →

What GPU do you need for Air Striker Mixtral 8x7B Instruct ZLoss?

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: the best quant that fits is IQ2_XS (13.7 GB file, about 15.2 GB in use).
  • 24 GB VRAM: the best quant that fits is Q3_K_S (20.4 GB file, about 22.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q4_K_M (28.4 GB file, about 30.0 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (38.4 GB file, about 40.0 GB in use).

Which Air Striker Mixtral 8x7B Instruct ZLoss quant should you choose?

Q4_K_M is the usual starting point for Air Striker Mixtral 8x7B Instruct ZLoss: it balances file size and quality well. Here it is a 28.4 GB file.

If memory is tight, the smallest file is IQ2_XXS at 12.3 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 byLoneStriker
FamilyMistral
Licenseapache-2.0
Downloads (HF)485
Last updated2024-01-27

Frequently asked questions about Air Striker Mixtral 8x7B Instruct ZLoss

How much VRAM does Air Striker Mixtral 8x7B Instruct ZLoss need?

About 30.0 GB at Q4_K_M with an 8K context window. That is the 28.4 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 Air Striker Mixtral 8x7B Instruct ZLoss on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Air Striker Mixtral 8x7B Instruct ZLoss GGUF?

It depends on the quant: IQ2_XXS is 12.3 GB, IQ2_XS is 13.7 GB, Q2_K is 17.3 GB, Q3_K_S is 20.4 GB, Q3_K_M is 22.5 GB, Q3_K_L is 24.2 GB and 5 more.

What context length does Air Striker Mixtral 8x7B Instruct ZLoss 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 Air Striker Mixtral 8x7B Instruct ZLoss GGUF?

The files are on Hugging Face in the LoneStriker/Air-Striker-Mixtral-8x7B-Instruct-ZLoss-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 Air Striker Mixtral 8x7B Instruct ZLoss 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.

Similar models

Browse all →

More from LoneStriker

All by LoneStriker →

More Mistral models

All Mistral →

Other large models

All large models →