Models

SOD-0.6B

Qwen3-0.6B-Sushi-Coder

Code-Llama-3-8B

Kimi-Dev-72B-mlx-fp16

Qwen3-0.6B-Code

WPAIGPT-fse-patterns-1

phi4-mini-mlx-16bit

NextCoder-32B

lumichat_coder-v2.1

snowflake_arctic_text2sql_r1_7b-nl2sqlpp-16bit-v5.7.8_phase_2-cw-16K

Qwen2.5-Coder-7B-20260302-MLX-2bit

qwen-1.7b-coder

Kimi-Dev-72B

Qwen2.5-Coder-32B

OpenCodeReasoning-Nemotron-14B

jupyter-agent-qwen3-4b-thinking

palmyra-mini

GeoCode-GPT

snowflake_arctic_text2sql_r1_7b-nl2sqlpp-16bit-v5.7.5_phase_1-cw-12K

Phi-4-mini-instruct-abliterated

Qwen3-4b-tcomanr-merge-v2.5

Qwen2.5-Coder-0.5B-Instruct-abliterated

Qwen2.5-3B-gabliterated-Dev

Sombrero-Opus-14B-Elite5

mypo-qwen2.5-coder-1.5b-dpo-v3

Qwen2.5-Coder-1.5B-Instruct-mlx-fp16

X-Coder-RL-Qwen2.5-7B

Qwen2.5-Coder-7B-20260302-MLX-8bit

DevStudio-Coder-1.5B

Qwen3-4b-tcomanr-merge-v2.3

Qwen2.5-Coder-7B-20260302-MERGED-16bit

Nemotron-Research-GooseReason-4B-Instruct-MLX-16bit

Qwen2.5-Interpreter

LocoTrainer-4B

Phi-4-mini-instruct-heretic

OpenCodeReasoning-Nemotron-32B-IOI

Qwen3-4B-Thinking-2507-DES-Reasoning

Qwen3-4B-ShiningValiant3

Qwen2.5-Coder-14B

KernelCoder

TigerCoder-1B

OpenSWE-32B