Mistral AI

Mistral Nemo 12B

12,2B

Parameters

7,0 Go

Q4_K_M file

≥ 8,5 Go

Recommended VRAM

131 072

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 8,5 Go (file + 4,000-token context). An estimate, not a measurement. Click a card for the detailed estimate.

Technical sheet

Published: 2024-07-17
Architecture: 40 layers · 8 KV heads · dimension 128
Attention: Standard: every layer keeps the whole context in memory.
Context cache (f16): ≈ 156 MB per 1,000 tokens · 5,0 Go for 32,768 tokens
GGUF file: bartowski/Mistral-Nemo-Instruct-2407-GGUF · Mistral-Nemo-Instruct-2407-Q4_K_M.gguf Download (7,0 Go)
Official repo: mistralai/Mistral-Nemo-Instruct-2407

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