LL

mistral 7b instruct v0.2.Q3 K S gguf on CPU via llama cpp

LlamaGGUF by JouChenLiuUpdated 2024-06-03
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant3.2 GB
Quick answer

mistral 7b instruct v0.2.Q3 K S gguf on CPU via llama cpp needs about 4.7 GB of memory at Q3_K_S (a 3.2 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

mistral 7b instruct v0.2.Q3 K S gguf on CPU via llama cpp is a 7.24B-parameter Llama model in GGUF format, quantized by JouChenLiu. Its trained context length is 32K tokens. The repository has 1 quant file, from 3.2 GB (Q3_K_S) to 3.2 GB (Q3_K_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S3.2 GB 4.7 GB
Fits Get file →

What GPU do you need for mistral 7b instruct v0.2.Q3 K S gguf on CPU via llama cpp?

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 Q3_K_S (3.2 GB file, about 4.7 GB in use).

Which mistral 7b instruct v0.2.Q3 K S gguf on CPU via llama cpp quant should you choose?

Q3_K_S (3.2 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.

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 byJouChenLiu
FamilyLlama
Downloads (HF)64
Last updated2024-06-03

Frequently asked questions about mistral 7b instruct v0.2.Q3 K S gguf on CPU via llama cpp

How much VRAM does mistral 7b instruct v0.2.Q3 K S gguf on CPU via llama cpp need?

About 4.7 GB at Q3_K_S with an 8K context window. That is the 3.2 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 7b instruct v0.2.Q3 K S gguf on CPU via llama cpp on an 8 GB GPU?

Yes, with Q3_K_S: the 3.2 GB file needs about 4.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of mistral 7b instruct v0.2.Q3 K S gguf on CPU via llama cpp GGUF?

It depends on the quant: Q3_K_S is 3.2 GB.

What context length does mistral 7b instruct v0.2.Q3 K S gguf on CPU via llama cpp 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 7b instruct v0.2.Q3 K S gguf on CPU via llama cpp GGUF?

The files are on Hugging Face in the JouChenLiu/mistral-7b-instruct-v0.2.Q3_K_S-gguf_on_CPU_via_llama-cpp 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 Llama models

All Llama →

Other small models

All small models →