Skip to content
NEWLive updates feed from Hugging Face, arXiv and GitHub  See what changed →

mistralai · mistral

Mistral-7B-Instruct-v0.2

Mistral-7B-Instruct-v0.2 by mistralai: a 7.2B-parameter dense open-weight model under the apache-2.0 license.

apache-2.0Dense33K contextAuto-imported · not yet reviewed

1,782,269 downloads · 3,231 likes · Model card · synced 2026-09-19

Specifications

Parameters
7.2B
Architecture
dense · mistral
Layers
32
Hidden size
4,096
KV heads · head dim
8 · 128
Vocabulary
32,000
Native dtype
bfloat16
Context window
32,768 tokens
Released
2023-12-11
Last modified on Hub
2025-07-24

Features & licensing

License
apache-2.0
Commercial use
Yes
Modalities
text
Tool / function calling
No
Reasoning mode
No
Languages
EN
Quantised variants on Hub
AWQ, EXL2, GGUF, GPTQ
Pipeline
text-generation
transformerspytorchsafetensorsmistraltext-generationfinetunedmistral-commonconversationaleval-resultstext-generation-inference

Task fit

Editorial scores (0–100) used by the recommendation engine.

  • Chat70
  • RAG / Q&A70
  • Code70
  • Summarisation70
  • Extraction70
  • Agents70

Hardware to run Mistral-7B-Instruct-v0.2

Weights need about 16 GB at FP16, 8 GB at INT8 and 5 GB at INT4. The KV cache adds roughly 131 MB per 1,000 tokens per request. For a reference workload of 5 requests per second with 1,500 input and 300 output tokens, total GPU memory is around 6.8 GB, which fits on 1 × NVIDIA A100 (80 GB).

GPU configurations at the reference workload
ConfigurationVRAMUtilisationEst. first tokenCloud / month
1 × NVIDIA L4 (24 GB)24 GB28 %~0.5 s$584
1 × NVIDIA L40S (48 GB)48 GB14 %~0.2 s$1,387
1 × NVIDIA A100 (80 GB)recommended80 GB9 %~0.1 s$2,336
1 × NVIDIA H100 (80 GB)80 GB9 %~0.0 s$3,285

Estimates only. Run an assessment for your own traffic.

Auto-imported from Hugging Face. Architecture, license and feature data are synced from the model repository; the task-fit scores below are provisional defaults until a curator reviews them.