MI

aixsatoshi Swallow MX 8x7b NVE chatvector Mixtral instruct

MistralGGUF by RichardErkhovUpdated 2024-10-13
Download on Hugging Face
Parameters46.7B
Context32K
Layers32
Architecturellama
Smallest quant17.3 GB
Quick answer

aixsatoshi Swallow MX 8x7b NVE chatvector Mixtral instruct needs about 22.0 GB of memory at Q3_K_S (a 20.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 7 quants, from 17.3 GB (Q2_K) to 22.5 GB (Q3_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

aixsatoshi Swallow MX 8x7b NVE chatvector Mixtral instruct is a 46.7B-parameter Mistral model in GGUF format, quantized by RichardErkhov. Its trained context length is 32K tokens. The repository has 7 quant files, from 17.3 GB (Q2_K) to 22.5 GB (Q3_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K17.3 GB 18.9 GB
Too big Get file →
IQ3_XS19.4 GB 20.9 GB
Too big Get file →
IQ3_S20.4 GB 22.0 GB
Too big Get file →
Q3_K_S20.4 GB 22.0 GB
Too big Get file →
IQ3_M21.4 GB 23.0 GB
Too big Get file →
Q3_K22.5 GB 24.1 GB
Too big Get file →
Q3_K_M22.5 GB 24.1 GB
Too big Get file →

What GPU do you need for aixsatoshi Swallow MX 8x7b NVE chatvector Mixtral instruct?

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: the best quant that fits is IQ3_M (21.4 GB file, about 23.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q3_K (22.5 GB file, about 24.1 GB in use).

Which aixsatoshi Swallow MX 8x7b NVE chatvector Mixtral instruct quant should you choose?

Q3_K_S (20.4 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 Q2_K at 17.3 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 byRichardErkhov
FamilyMistral
Licenseapache-2.0
Downloads (HF)34
Last updated2024-10-13

Frequently asked questions about aixsatoshi Swallow MX 8x7b NVE chatvector Mixtral instruct

How much VRAM does aixsatoshi Swallow MX 8x7b NVE chatvector Mixtral instruct need?

About 22.0 GB at Q3_K_S with an 8K context window. That is the 20.4 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 aixsatoshi Swallow MX 8x7b NVE chatvector Mixtral instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 18.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of aixsatoshi Swallow MX 8x7b NVE chatvector Mixtral instruct GGUF?

It depends on the quant: Q2_K is 17.3 GB, IQ3_XS is 19.4 GB, IQ3_S is 20.4 GB, Q3_K_S is 20.4 GB, IQ3_M is 21.4 GB, Q3_K is 22.5 GB and 1 more.

What context length does aixsatoshi Swallow MX 8x7b NVE chatvector Mixtral instruct 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 aixsatoshi Swallow MX 8x7b NVE chatvector Mixtral instruct GGUF?

The files are on Hugging Face in the RichardErkhov/aixsatoshi_-_Swallow-MX-8x7b-NVE-chatvector-Mixtral-instruct-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 aixsatoshi Swallow MX 8x7b NVE chatvector Mixtral instruct 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 RichardErkhov

All by RichardErkhov →

More Mistral models

All Mistral →

Other large models

All large models →