MI

mistral base bnb 4bit alpaca lora adaptor merged

MistralGGUF by shidowakeUpdated 2024-01-13
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant5.9 GB
Quick answer

mistral base bnb 4bit alpaca lora adaptor merged needs about 7.5 GB of memory at Q6_K (a 5.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

mistral base bnb 4bit alpaca lora adaptor merged is a 7.24B-parameter Mistral model in GGUF format, quantized by shidowake. Its trained context length is 32K tokens. The repository has 1 quant file, from 5.9 GB (Q6_K) to 5.9 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K5.9 GB 7.5 GB
Tight Get file →

What GPU do you need for mistral base bnb 4bit alpaca lora adaptor merged?

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: the best quant that fits is Q6_K (5.9 GB file, about 7.5 GB in use).

Which mistral base bnb 4bit alpaca lora adaptor merged quant should you choose?

Q6_K (5.9 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

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 byshidowake
FamilyMistral
Downloads (HF)13
Last updated2024-01-13

Frequently asked questions about mistral base bnb 4bit alpaca lora adaptor merged

How much VRAM does mistral base bnb 4bit alpaca lora adaptor merged need?

About 7.5 GB at Q6_K with an 8K context window. That is the 5.9 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 mistral base bnb 4bit alpaca lora adaptor merged on an 8 GB GPU?

Yes, with Q6_K: the 5.9 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of mistral base bnb 4bit alpaca lora adaptor merged GGUF?

It depends on the quant: Q6_K is 5.9 GB.

What context length does mistral base bnb 4bit alpaca lora adaptor merged 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 mistral base bnb 4bit alpaca lora adaptor merged GGUF?

The files are on Hugging Face in the shidowake/mistral-base-bnb-4bit-alpaca-lora-adaptor-merged-GGUF 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 shidowake

All by shidowake →

More Mistral models

All Mistral →

Other small models

All small models →