LocalOps
Back to Calculator

Leanstral 24B

Mistral AI's Lean 4 theorem prover model — a 24B open-weight model fine-tuned for generating formally verifiable proofs in the Lean 4 language.

Model Specifications

ArchitectureTEXT
Parameters24B
Familymistral
VRAM (Q4)12.0GB
Released alongside Mistral Small 4. Specialized for Lean 4 output; not a general-purpose model.
#mistral#math#lean4#formal-proofs#science#apache2Source

Estimated Quantization Sizes

FormatPrecisionEst. VRAMRecommendation
FP16 / BF1616-bit48.0 GBUncompressed Base
Q8_0High8-bit24.0 GBNear Lossless
Q6_K6-bit18.0 GBExcellent Balance
Q4_K_MPopular4-bit12.0 GBStandard Use

Share this Model

Send this model's specs directly to your community.

Post