MI

Noromaid v0.4 Mixtral Instruct 8x7b Zloss

MistralGGUF by Artefact2Updated 2024-02-11
Download on Hugging Face
Parameters46.7B
Context32K
Layers32
Architecturellama
Smallest quant12.3 GB
Quick answer

Noromaid v0.4 Mixtral Instruct 8x7b Zloss needs about 19.9 GB of memory at IQ3_XXS (a 18.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 10 quants, from 12.3 GB (IQ2_XXS) to 32.2 GB (Q5_K_S). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Noromaid v0.4 Mixtral Instruct 8x7b Zloss is a 46.7B-parameter Mistral model in GGUF format, quantized by Artefact2. Its trained context length is 32K tokens. The repository has 10 quant files, from 12.3 GB (IQ2_XXS) to 32.2 GB (Q5_K_S).

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_K_S16.0 GB 17.6 GB
Too big Get file →
Q2_K17.3 GB 18.9 GB
Too big Get file →
IQ3_XXS18.3 GB 19.9 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 →
Q5_K_S32.2 GB 33.8 GB
Too big Get file →

What GPU do you need for Noromaid v0.4 Mixtral Instruct 8x7b 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_S (26.7 GB file, about 28.3 GB in use).
  • 48 GB VRAM: the best quant that fits is Q5_K_S (32.2 GB file, about 33.8 GB in use).

Which Noromaid v0.4 Mixtral Instruct 8x7b Zloss quant should you choose?

IQ3_XXS (18.3 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

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 byArtefact2
FamilyMistral
Downloads (HF)225
Last updated2024-02-11

Frequently asked questions about Noromaid v0.4 Mixtral Instruct 8x7b Zloss

How much VRAM does Noromaid v0.4 Mixtral Instruct 8x7b Zloss need?

About 19.9 GB at IQ3_XXS with an 8K context window. That is the 18.3 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 Noromaid v0.4 Mixtral Instruct 8x7b 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 Noromaid v0.4 Mixtral Instruct 8x7b Zloss GGUF?

It depends on the quant: IQ2_XXS is 12.3 GB, IQ2_XS is 13.7 GB, Q2_K_S is 16.0 GB, Q2_K is 17.3 GB, IQ3_XXS is 18.3 GB, Q3_K_S is 20.4 GB and 4 more.

What context length does Noromaid v0.4 Mixtral Instruct 8x7b 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 Noromaid v0.4 Mixtral Instruct 8x7b Zloss GGUF?

The files are on Hugging Face in the Artefact2/Noromaid-v0.4-Mixtral-Instruct-8x7b-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 Noromaid v0.4 Mixtral Instruct 8x7b Zloss 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.

Similar models

Browse all →

More from Artefact2

All by Artefact2 →

More Mistral models

All Mistral →

Other large models

All large models →