MI

GLEAM Mixtral 8x7B Instruct GGUF v1

MistralGGUF by TxokaUpdated 2024-06-03
Download on Hugging Face
Parameters46.7B
Context32K
Layers32
Architecturellama
Smallest quant28.4 GB
Quick answer

GLEAM Mixtral 8x7B Instruct GGUF v1 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. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

GLEAM Mixtral 8x7B Instruct GGUF v1 is a 46.7B-parameter Mistral model in GGUF format, quantized by Txoka. Its trained context length is 32K tokens. The repository has 1 quant file, from 28.4 GB (Q4_K_M) to 28.4 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M28.4 GB 30.0 GB
Too big Get file →

What GPU do you need for GLEAM Mixtral 8x7B Instruct GGUF 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 Q4_K_M (28.4 GB file, about 30.0 GB in use).

Which GLEAM Mixtral 8x7B Instruct GGUF v1 quant should you choose?

Q4_K_M is the usual starting point for GLEAM Mixtral 8x7B Instruct GGUF v1: it balances file size and quality well. Here it is a 28.4 GB file.

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 byTxoka
FamilyMistral
Downloads (HF)7
Last updated2024-06-03

Frequently asked questions about GLEAM Mixtral 8x7B Instruct GGUF v1

How much VRAM does GLEAM Mixtral 8x7B Instruct GGUF v1 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 GLEAM Mixtral 8x7B Instruct GGUF v1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 30.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of GLEAM Mixtral 8x7B Instruct GGUF v1 GGUF?

It depends on the quant: Q4_K_M is 28.4 GB.

What context length does GLEAM Mixtral 8x7B Instruct GGUF v1 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 GLEAM Mixtral 8x7B Instruct GGUF v1 GGUF?

The files are on Hugging Face in the Txoka/GLEAM-Mixtral-8x7B-Instruct-GGUF-v1 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from Txoka

All by Txoka →

More Mistral models

All Mistral →

Other large models

All large models →