Open Models, Ready for Production

HanningZhang

deepseek_only_conjecture_claude_deepseek_train_data_max1_5e-7_bs32_decay1e-6_2ep_ep1

qwen-abs-4b-fewshot8-0109-epoch4

qwen-abs-4b-fewshot8-0109-epoch1

qwen-abs-4b-fewshot8-0109-epoch6

qwen-abs-4b-fewshot8-0109-epoch5

Elfsong

Qwen3_4B_Arabic_400

DeepSeek-R1-Pruned-108B

Elfsong

Qwen3_4B_Arabic_200

DeepSeek-R1-Pruned-50B

ShweYon-Qwen2.5-Burmese-0.5B-it1.0

DeepSeek-R1-Pruned-61B

whisper-finetuned-model

mstyslavity

monad_random_experimental

MiniMax-M2.1-REAP-30-REPAIR-IN-PROGRESS

Athena-24B-Base

Qwen2.5-3B-Instruct-emergent-finetune-train_full_context-all-full-r32

DeepSeek-R1-Pruned-34B

Alhambra

qwen-abs-4b-fewshot1-0109-epoch3

qwen-abs-4b-fewshot1-0109-epoch4

qwen-abs-4b-fewshot1-0109-epoch1

qwen-abs-4b-fewshot1-0109-epoch6

qwen-abs-4b-fewshot1-0109-epoch2

qwen-abs-4b-fewshot1-0109-epoch5

alexgusevski

Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning-mlx-fp16

bfm2-mntp

scasella91

timecapsulellm-pr1

follow-up-q-grpo-model-v1-merged

nunchaku-flux.1-schnell-pix2pix-turbo

content-function-gemma

udm_qwen2.5-1.5b-Instruct

alexgusevski

Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning-mlx-8Bit

alexgusevski

Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning-mlx-2Bit

alexgusevski

Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning-mlx-4Bit

alexgusevski

Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning-mlx-3Bit

alexgusevski

Llama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning-mlx-fp16

alexgusevski

Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning-mlx-6Bit

koutch

short_paper_llama_1.json_train_dpo_v2_train_no_think

alexgusevski

Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning-mlx-5Bit

usmanxia

gemma3-12b-pak-orpo-merged

alexgusevski

Llama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning-mlx-2Bit

alexgusevski

Llama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning-mlx-3Bit