24B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.
1.2M Pulls 6 Tags Updated 9 months ago
123B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.
357.1K Pulls 5 Tags Updated 9 months ago
Devstral: the best open source model for coding agents
1M Pulls 5 Tags Updated 1 year ago
A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
3.8M Pulls 5 Tags Updated 1 year ago
A strong, economical, and efficient Mixture-of-Experts language model.
1.2M Pulls 34 Tags Updated 2 years ago
MathΣtral: a 7B model designed for math reasoning and scientific discovery by Mistral AI.
554.5K Pulls 17 Tags Updated 2 years ago
Dolphin 2.9 is a new model with 8B and 70B sizes by Eric Hartford based on Llama 3 that has a variety of instruction, conversational, and coding skills.
2.1M Pulls 53 Tags Updated 2 years ago
An upgraded version of DeekSeek-V2 that integrates the general and coding abilities of both DeepSeek-V2-Chat and DeepSeek-Coder-V2-Instruct.
291.1K Pulls 7 Tags Updated 2 years ago
Quantized Q4_K_S version of Devstral small 2 24B FP16 model
158 Pulls 1 Tag Updated 2 months ago
Quantized Q4_K_S version of Devstral small 24B FP16 model
65 Pulls 1 Tag Updated 1 month ago
Abliterated (Uncensored) Devstral Small 2
2,772 Pulls 12 Tags Updated 9 months ago
Devstral 2 Small but with parameters and templates.
342 Pulls 3 Tags Updated 7 months ago
Generates good programming code, command line help, etc. Compatible with opencode .
120 Pulls 1 Tag Updated 9 months ago
Various Quants of Fused Devstral 1.1 (2507).
87 Pulls 2 Tags Updated 10 months ago
Various Quants of Devstral 1.1 (2507).
51 Pulls 3 Tags Updated 10 months ago
This is an uncensored version of mistralai/Devstral-Small-2505 created with abliteration
4,317 Pulls 6 Tags Updated 1 year ago
Devstral is an agentic LLM for software engineering tasks. Devstral 2 models excel at using tools to explore codebases, editing multiple files and power software engineering agents. The model achieves remarkable performance on SWE-bench.
1,333 Pulls 3 Tags Updated 7 months ago
Made from Devstral with temperature very high, and num_ctx low. Not sure how this will work, try with caution.
2 Pulls 1 Tag Updated 1 year ago
40 Pulls 1 Tag Updated 5 months ago
24 Pulls 1 Tag Updated 5 months ago