alexgusevski/Reverb-7b-q3-mlx

Text Generation • 1.0B • Updated Feb 20 • 4

Note Reverb 7B

alexgusevski/Dolphin3.0-Qwen2.5-3b-q3-mlx

0.4B • Updated Feb 21 • 12

Note Dolphin 3.0 Qwen 2.5 3B

alexgusevski/EXAONE-3.5-2.4B-Instruct-q3-mlx

Text Generation • 0.3B • Updated Feb 21 • 2

Note Exaone 3.5 2.4B

alexgusevski/EXAONE-3.5-7.8B-Instruct-q3-mlx

Text Generation • 1.0B • Updated Feb 21 • 3

Note Exaone 3.5 7.8B

alexgusevski/Lucie-7B-q3-mlx

Text Generation • 0.8B • Updated Feb 22 • 3

Note Lucie 7B

alexgusevski/Lucie-7B-Instruct-v1.1-q3-mlx

Text Generation • 0.8B • Updated Feb 22 • 2

Note Lucie 7B Instruct

alexgusevski/Lucie-7B-Instruct-human-data-q3-mlx

Text Generation • 0.8B • Updated Feb 22 • 5

Note Lucie 7B Instruct human data

alexgusevski/Qwen2.5-Coder-3B-q3-mlx

Text Generation • 0.4B • Updated Feb 22 • 3

Note Qwen 2.5 Coder 3B

alexgusevski/Qwen2.5-Coder-7B-q3-mlx

Text Generation • 1.0B • Updated Feb 23 • 9

Note Qwen 2.5 Coder 7B

alexgusevski/Chirp-3B-q3-mlx

0.4B • Updated Feb 23 • 2

Note Chirp 3B

alexgusevski/UIGEN-T1.1-Qwen-7b-q3-mlx

Text Generation • 1.0B • Updated Feb 23 • 41

Note UIGEN T1.1 Qwen 7B

alexgusevski/Qwen2.5-Coder-3B-Instruct-q3-mlx

Text Generation • 0.4B • Updated Feb 24 • 5

Note Qwen 2.5 Coder 3B Instruct

alexgusevski/Qwen2.5-Coder-7B-Instruct-q3-mlx

Text Generation • 1.0B • Updated Feb 24 • 7

Note Qwen 2.5 Coder 7B Instruct

alexgusevski/Arcee-Maestro-7B-Preview-q3-mlx

Text Generation • 1.0B • Updated Feb 24 • 2

Note Arcee Maestro 7B Preview

alexgusevski/ReaderLM-v2-q3-mlx

Text Generation • 0.2B • Updated Feb 24 • 5

Note ReaderLM V2 (1.5B)

alexgusevski/OpenThinker-7B-q3-mlx

Text Generation • 1.0B • Updated Feb 24 • 2

Note OpenThinker 7B

alexgusevski/Fino1-8B-q3-mlx

Text Generation • 1B • Updated Feb 24 • 3

Note Fino1 8B

alexgusevski/Ministral-8B-Instruct-2410-q3-mlx

1B • Updated Feb 25 • 3

Note Ministral 8B Instruct

alexgusevski/LLaMA-Mesh-q3-mlx

Text-to-3D • 1B • Updated Feb 25 • 7

Note LLama Mesh (8B)

alexgusevski/DeepSeek-R1-DRAFT-Qwen2.5-0.5B-q3-mlx

Text Generation • 0.1B • Updated Feb 26 • 7

Note DeepSeek R1 DRAFT Qwen 2.5 0.5B

alexgusevski/Selene-1-Mini-Llama-3.1-8B-q3-mlx

Text Generation • 1B • Updated Feb 26 • 10

Note Selene 1 Mini Llama 3.1 8B

alexgusevski/granite-3.2-2b-instruct-q3-mlx

Text Generation • 0.3B • Updated Feb 26 • 5

Note Granite 3.2 2B Instruct

alexgusevski/Meta-Llama-3.1-8B-SurviveV3-q3-mlx

1B • Updated Mar 4 • 22

Note Llama 3.1 8B SurviveV3

alexgusevski/Phi-4-mini-instruct-Q2-mlx

Text Generation • 0.4B • Updated Mar 4 • 7

Note Phi 4 mini instruct

alexgusevski/Fallen-Llama-3.3-R1-70B-v1-Q3-mlx

9B • Updated Mar 4 • 42

Note Fallen Llama 3.3 R1 70B V1

alexgusevski/olmOCR-7B-0225-preview-q3-mlx

Image-to-Text • 1B • Updated Mar 5 • 263

Note olmOCR 7B 0225 preview

alexgusevski/QwQ-32B-6bit

Text Generation • 7B • Updated Mar 5 • 5

Note QwQ 32B

alexgusevski/Goppa-LogiLlama-mlx-2Bit

Text Generation • 0.1B • Updated Mar 13 • 2

Note Goppa LogiLLamaa (Llama 3.2, 1B)

alexgusevski/OlympicCoder-7B-mlx-2Bit

Text Generation • 0.7B • Updated Mar 13 • 5

Note Olympic Coder 7B

alexgusevski/OlympicCoder-32B-mlx-2Bit

Text Generation • 3B • Updated Mar 13 • 5

Note Olympic Coder 32B

alexgusevski/gemma-3-text-1b-it-q3-mlx

Text Generation • 0.2B • Updated Mar 17 • 6

Note Gemma 3 1B, converted with --dtype bfloat16 and working properly in LM studio

alexgusevski/gemma-3-text-4b-it-q3-mlx

Text Generation • 0.6B • Updated Mar 18 • 7

Note Gemma 3 4B Text only

alexgusevski/EXAONE-Deep-2.4B-q3-mlx

Text Generation • 0.3B • Updated Mar 18 • 7

Note Exaone Deep 2.4B (don't forget to change prompt template according to https://github.com/LG-AI-EXAONE/EXAONE-Deep?tab=readme-ov-file#lm-studio)

alexgusevski/EXAONE-Deep-7.8B-mlx-3Bit

Text Generation • 1.0B • Updated Mar 18 • 5

Note Exaone Deep 7.8B (don't forget to change prompt template according to https://github.com/LG-AI-EXAONE/EXAONE-Deep?tab=readme-ov-file#lm-studio)

alexgusevski/EXAONE-Deep-32B-mlx-3Bit

Text Generation • 4B • Updated Mar 18 • 5

Note Exaone Deep 32B (don't forget to change prompt template according to https://github.com/LG-AI-EXAONE/EXAONE-Deep?tab=readme-ov-file#lm-studio)

alexgusevski/openhands-lm-32b-v0.1-mlx-3Bit

Text Generation • 4B • Updated Mar 31 • 6

Note Openhands LM 32B