MI

openbuddy-mixtral-7bx8-v18.1-32k

MistralGGUF by LoneStrikerUpdated 2024-02-14
Download on Hugging Face
Parameters46.7B
Context32K
Layers32
Architecturellama
Smallest quant17.3 GB
Quick answer

openbuddy-mixtral-7bx8-v18.1-32k needs about 30.0 GB of memory at Q4_K_M (a 28.5 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 9 quants, from 17.3 GB (Q2_K) to 38.4 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

openbuddy-mixtral-7bx8-v18.1-32k is a 46.7B-parameter Mistral model in GGUF format, quantized by LoneStriker. Its trained context length is 32K tokens. The repository has 9 quant files, from 17.3 GB (Q2_K) to 38.4 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K17.3 GB 18.9 GB
Too big Get file →
Q3_K_S20.5 GB 22.0 GB
Too big Get file →
Q3_K_M22.6 GB 24.1 GB
Too big Get file →
Q3_K_L24.2 GB 25.8 GB
Too big Get file →
Q4_K_S26.8 GB 28.3 GB
Too big Get file →
Q4_K_M28.5 GB 30.0 GB
Too big Get file →
Q5_K_S32.3 GB 33.8 GB
Too big Get file →
Q5_K_M33.3 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 openbuddy-mixtral-7bx8-v18.1-32k?

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 Q3_K_S (20.5 GB file, about 22.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q4_K_M (28.5 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 openbuddy-mixtral-7bx8-v18.1-32k quant should you choose?

Q4_K_M is the usual starting point for openbuddy-mixtral-7bx8-v18.1-32k: it balances file size and quality well. Here it is a 28.5 GB file.

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 byLoneStriker
FamilyMistral
Licenseapache-2.0
Downloads (HF)291
Last updated2024-02-14

Frequently asked questions about openbuddy-mixtral-7bx8-v18.1-32k

How much VRAM does openbuddy-mixtral-7bx8-v18.1-32k need?

About 30.0 GB at Q4_K_M with an 8K context window. That is the 28.5 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 openbuddy-mixtral-7bx8-v18.1-32k 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 openbuddy-mixtral-7bx8-v18.1-32k GGUF?

It depends on the quant: Q2_K is 17.3 GB, Q3_K_S is 20.5 GB, Q3_K_M is 22.6 GB, Q3_K_L is 24.2 GB, Q4_K_S is 26.8 GB, Q4_K_M is 28.5 GB and 3 more.

What context length does openbuddy-mixtral-7bx8-v18.1-32k 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 openbuddy-mixtral-7bx8-v18.1-32k GGUF?

The files are on Hugging Face in the LoneStriker/openbuddy-mixtral-7bx8-v18.1-32k-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 openbuddy-mixtral-7bx8-v18.1-32k 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 →