MI

gguf merged model3 21022024

MistralGGUF by danielhanchenUpdated 2024-02-20
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant4.4 GB
Quick answer

gguf merged model3 21022024 needs about 5.9 GB of memory at Q4_K_M (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 4.4 GB (Q4_K_M) to 7.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

gguf merged model3 21022024 is a 7.24B-parameter Mistral model in GGUF format, quantized by danielhanchen. Its trained context length is 32K tokens. The repository has 2 quant files, from 4.4 GB (Q4_K_M) to 7.7 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M4.4 GB 5.9 GB
Fits Get file →
Q8_07.7 GB 9.3 GB
Too big Get file →

What GPU do you need for gguf merged model3 21022024?

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: the best quant that fits is Q4_K_M (4.4 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_K_M (4.4 GB file, about 5.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.7 GB file, about 9.3 GB in use).

Which gguf merged model3 21022024 quant should you choose?

Q4_K_M is the usual starting point for gguf merged model3 21022024: it balances file size and quality well. Here it is a 4.4 GB file.

The Q8_0 file is 7.7 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters7.24B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bydanielhanchen
FamilyMistral
Licenseapache-2.0
Downloads (HF)38
Last updated2024-02-20

Frequently asked questions about gguf merged model3 21022024

How much VRAM does gguf merged model3 21022024 need?

About 5.9 GB at Q4_K_M with an 8K context window. That is the 4.4 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 gguf merged model3 21022024 on an 8 GB GPU?

Yes, with Q4_K_M: the 4.4 GB file needs about 5.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of gguf merged model3 21022024 GGUF?

It depends on the quant: Q4_K_M is 4.4 GB, Q8_0 is 7.7 GB.

What context length does gguf merged model3 21022024 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 gguf merged model3 21022024 GGUF?

The files are on Hugging Face in the danielhanchen/gguf_merged_model3_21022024 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does gguf merged model3 21022024 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.

Other GGUFs of mistral-7b-bnb-4bit

Similar models

Browse all →

More from danielhanchen

All by danielhanchen →

More Mistral models

All Mistral →

Other small models

All small models →