Mistral 7B v0.3

Mistral AI · Mistral family · released 2024-05-22 · Apache-2.0 license

Mistral 7B v0.3 by Mistral AI — 7B open-weight local LLM. License: Apache-2.0. Benchmarks, VRAM requirements per quantization, GPU compatibility, pricing and community reviews on slopsome.com.

Key specs

TypeLocal open-weight
Parameters7B total
Architecture
Context window33K tokens
Knowledge cutoff
Modalitiestext
Recommended backends
Minimum viable rig

Benchmark scores

GPQA Diamond26%
SWE-bench Verified10%
AIME12%
MMLU-Pro42%
BFCL v3 (tool use)55%
Composite score11.37
Community ratingNo reviews yet

VRAM & disk per quantization

QuantVRAMDiskRAMContext
Q4_K_M5 GB5 GB8 GB33K