LocalOps
Back to Calculator

Devstral Small 1.1

Open-weight 24B coding agent model by Mistral + All Hands AI. Fine-tuned from Mistral Small 3.1 under Apache 2.0. 128K context window, supports Mistral-style function calling and XML output. Runs on a single RTX 4090.

Model Specifications

ArchitectureTEXT
Parameters24B
Familydevstral
VRAM (Q4)12.0GB
#mistral#coding#agentic#apache2#open-source#swe-bench#function-callingSource

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