Model catalog

Mistral Nemo 12B Instruct

A 12B Mistral and NVIDIA collaboration model, extending the catalog into a larger multilingual instruction tier.

Check this model on your hardware See what your PC can run

Model overview

Family: Mistral Nemo
Provider: Mistral AI / NVIDIA
Architecture: Mistral
Parameters: 12B
Formats: gguf, safetensors
Runtimes: llama.cpp
License: Apache-2.0
Maximum context: 131,072 tokens

Available quantizations

Lower-bit quantizations generally use less memory. The compatibility calculator uses these candidates and its transparent approximate memory assumptions; it does not make a performance guarantee.

Q4_K_M

A commonly available lower-memory GGUF variant; the listed memory input is an estimate, not the repository file size.

Bits per weight: 4.5
Source: QuantFactory/Mistral-Nemo-Instruct-2407-GGUF GGUF repository

Q8_0

A higher-memory GGUF variant where listed by the conversion repository; the listed memory input remains approximate.

Bits per weight: 8
Source: QuantFactory/Mistral-Nemo-Instruct-2407-GGUF GGUF repository

Compatibility notes

Weight estimates are approximate and include a runtime overhead. Real requirements vary with context length, runtime, drivers, and other system use. A model page cannot determine compatibility without your hardware profile; use the calculator for that assessment.

Mistral Nemo Instruct 2407 model card; verified value, last verified 2026-09-23. Publisher model card identifies the 12B model and Apache-2.0 license. Quantization files are a community conversion and the 128K limit is not a hardware-fit claim. View source