Mistral AI's 7B instruction-tuned model, version 0.3. Compared with earlier releases it carries an extended 32,768-token vocabulary and support for function calling.

Its reputation is for fluent, natural prose, which makes it a comfortable choice for drafting and rewriting. Apache 2.0 licensed, so there are no usage restrictions to pass along.

Specifications


Parameters	7B
Quantization	Q4_K_M
File size	4.07 GB
Minimum RAM	8.00 GB
Minimum VRAM	6.00 GB
Context length	32,768 tokens
SHA-256	`1270d22c0fbb3d092fb725d4d96c457b7b687a5f5a715abe1e818da303e562b6`

Single file: Mistral-7B-Instruct-v0.3-Q4_K_M.gguf

Quantization

Quantization performed at the Faculty of Engineering, McMaster University.

The GGUF conversion this build is derived from was produced by bartowski, and the weights here are a byte-for-byte copy of that file — the SHA-256 above matches the upstream artifact.

Provenance

Original model: mistralai/Mistral-7B-Instruct-v0.3
Upstream GGUF: bartowski/Mistral-7B-Instruct-v0.3-GGUF
Mirrored for Solus, a desktop app for running language models entirely on your own machine.

Usage

llama-cli -m Mistral-7B-Instruct-v0.3-Q4_K_M.gguf -cnv

Fazmin/solus_v1_mistral-7b-instruct-v0.3-q4

Mistral 7B Instruct v0.3 — Solus v1

Specifications

Quantization

Provenance

Usage

Fazmin/
solus_v1_mistral-7b-instruct-v0.3-q4