gemma3-4b

CEIA-UFG/Gemma-3-Gaia-PT-BR-4b-it

qwen2-1b5

SpiceRL/DRA-GRPO

qwen2-1b5

SpiceRL/DRA-DR.GRPO

qwen3-0b6

PirxTion/qwen3-dpo-tulu

qwen3-0b6

andresnowak/Qwen3-0.6B-instruction-finetuned

qwen3-4b

Qwen/Qwen3-4B-MLX-bf16

qwen3-8b

Qwen/Qwen3-8B-MLX-bf16

qwen3-1b7

Qwen/Qwen3-1.7B-MLX-bf16

qwen3-0b6

Qwen/Qwen3-0.6B-MLX-bf16

qwen3-4b

EmergentMethods/Qwen3-4B-BiasExpert

qwen3-0b6

thesantatitan/qwen3-0.6B-svg-sft

qwen2-7b

Snowflake/Arctic-Text2SQL-R1-7B

qwen2-7b

nvidia/AceReason-Nemotron-7B

llama32-3b

benjaminsinzore/Basqui-R1-4B-v1

qwen25-7b

open-r1/OpenR1-Distill-7B

qwen2-32b

ArliAI/QwQ-32B-ArliAI-RpR-v4

qwen2-7b

PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-7b-em-ppo-v0.3

qwen25-3b

PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-3b-em-grpo-v0.3

llama31-8b

maldv/praxis-bookwriter-llama3.1-8b-sft

mistral-24b

unsloth/Devstral-Small-2505