Mistral AI

Ministral 3 3B

small machinesvision

3,8B

Parameters

2,0 Go

Q4_K_M file

≥ 3,5 Go

Recommended VRAM

262 144

Max context

Not measured yet

No card has run the TokenBench protocol on this model yet. The current protocol covers a selection of models; benchmarking any catalog model from the app is coming soon.

Measure my card →

Which cards should it fit on?

Cards on the site whose video memory covers the recommended 3,5 Go (file + 4,000-token context). An estimate, not a measurement. Click a card for the detailed estimate.

Technical sheet

Published
2025-10-31
Architecture
26 layers · 8 KV heads · dimension 128
Attention
Standard: every layer keeps the whole context in memory.
Context cache (f16)
≈ 102 MB per 1,000 tokens · 3,3 Go for 32,768 tokens
GGUF file
bartowski/mistralai_Ministral-3-3B-Instruct-2512-GGUF · mistralai_Ministral-3-3B-Instruct-2512-Q4_K_M.gguf Download (2,0 Go)

Public Hugging Face data (official config.json, GGUF repo). The context cache only counts full-attention layers.