-
warshanks/Qwen3-30B-A3B-Instruct-2507-AWQ
Text Generation • 5B • Updated • 85 -
warshanks/Qwen3-16B-A3B-abliterated-AWQ
Text Generation • 3B • Updated • 4 -
warshanks/Huihui-Qwen3-14B-abliterated-v2-AWQ
Text Generation • 3B • Updated • 308 • 2 -
warshanks/Qwen3-8B-abliterated-AWQ
Text Generation • 2B • Updated • 4
Ben Shankles PRO
warshanks
AI & ML interests
MLX, AWQ, GPTQ
Recent Activity
new activity
7 days ago
LiquidAI/LFM2-350M-ENJP-MT-GGUF:Sensitive to Quantization
updated
a model
20 days ago
warshanks/Hermes-4-14B-AWQ
Organizations
W4A16 quants made with llmcompressor
MedGemma MLX conversions I've done
-
mlx-community/medgemma-4b-it-4bit
Image-Text-to-Text • 0.9B • Updated • 1.06k • 2 -
mlx-community/medgemma-4b-it-6bit
Image-Text-to-Text • 1B • Updated • 18 • 1 -
mlx-community/medgemma-4b-it-8bit
Image-Text-to-Text • 1B • Updated • 36 • 1 -
mlx-community/medgemma-4b-it-bf16
Image-Text-to-Text • 5B • Updated • 1.07k • 1
DeepSeek MLX conversions I've done
-
mlx-community/DeepSeek-R1-0528-Qwen3-8B-4bit
Text Generation • 1B • Updated • 1.34k • 4 -
mlx-community/DeepSeek-R1-0528-Qwen3-8B-6bit
Text Generation • 8B • Updated • 29 • 1 -
mlx-community/DeepSeek-R1-0528-Qwen3-8B-8bit
Text Generation • 2B • Updated • 1.09k • 1 -
mlx-community/DeepSeek-R1-0528-Qwen3-8B-bf16
Text Generation • 8B • Updated • 1.1k • • 2
Nemotron MLX conversions I've done
-
mlx-community/AceReason-Nemotron-7B-4bit
Text Generation • 1B • Updated • 41 -
mlx-community/AceReason-Nemotron-7B-8bit
Text Generation • 2B • Updated • 7 -
mlx-community/AceReason-Nemotron-7B-bf16
Text Generation • 8B • Updated • 10 -
mlx-community/AceReason-Nemotron-1.1-7B-4bit
Text Generation • 1B • Updated • 17
Abliterated model conversions to MLX
-
mlx-community/Josiefied-Health-Qwen3-8B-abliterated-v1-4bit
Text Generation • 1B • Updated • 29 -
mlx-community/Josiefied-Health-Qwen3-8B-abliterated-v1-8bit
Text Generation • 2B • Updated • 20 -
mlx-community/Josiefied-Health-Qwen3-8B-abliterated-v1-bf16
Text Generation • 8B • Updated • 33 • 1 -
mlx-community/Josiefied-DeepSeek-R1-0528-Qwen3-8B-abliterated-v1-4bit
Text Generation • 1B • Updated • 1.14k • 1
Menlo Research Quantizations
Mistral Quantizations
Lingshu MLX conversions
-
Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning
Paper • 2506.07044 • Published • 113 -
mlx-community/Lingshu-7B-4bit
Image-Text-to-Text • 1B • Updated • 9 -
mlx-community/Lingshu-7B-6bit
Image-Text-to-Text • Updated • 9 -
mlx-community/Lingshu-7B-8bit
Image-Text-to-Text • Updated • 10
Healthcare oriented LLM conversions to MLX
-
mlx-community/medgemma-4b-it-4bit
Image-Text-to-Text • 0.9B • Updated • 1.06k • 2 -
mlx-community/medgemma-4b-it-6bit
Image-Text-to-Text • 1B • Updated • 18 • 1 -
mlx-community/medgemma-4b-it-8bit
Image-Text-to-Text • 1B • Updated • 36 • 1 -
mlx-community/medgemma-4b-it-bf16
Image-Text-to-Text • 5B • Updated • 1.07k • 1
TheDrummer MLX model conversions I've done
-
warshanks/Qwen3-30B-A3B-Instruct-2507-AWQ
Text Generation • 5B • Updated • 85 -
warshanks/Qwen3-16B-A3B-abliterated-AWQ
Text Generation • 3B • Updated • 4 -
warshanks/Huihui-Qwen3-14B-abliterated-v2-AWQ
Text Generation • 3B • Updated • 308 • 2 -
warshanks/Qwen3-8B-abliterated-AWQ
Text Generation • 2B • Updated • 4
Menlo Research Quantizations
W4A16 quants made with llmcompressor
Mistral Quantizations
MedGemma MLX conversions I've done
-
mlx-community/medgemma-4b-it-4bit
Image-Text-to-Text • 0.9B • Updated • 1.06k • 2 -
mlx-community/medgemma-4b-it-6bit
Image-Text-to-Text • 1B • Updated • 18 • 1 -
mlx-community/medgemma-4b-it-8bit
Image-Text-to-Text • 1B • Updated • 36 • 1 -
mlx-community/medgemma-4b-it-bf16
Image-Text-to-Text • 5B • Updated • 1.07k • 1
Lingshu MLX conversions
-
Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning
Paper • 2506.07044 • Published • 113 -
mlx-community/Lingshu-7B-4bit
Image-Text-to-Text • 1B • Updated • 9 -
mlx-community/Lingshu-7B-6bit
Image-Text-to-Text • Updated • 9 -
mlx-community/Lingshu-7B-8bit
Image-Text-to-Text • Updated • 10
DeepSeek MLX conversions I've done
-
mlx-community/DeepSeek-R1-0528-Qwen3-8B-4bit
Text Generation • 1B • Updated • 1.34k • 4 -
mlx-community/DeepSeek-R1-0528-Qwen3-8B-6bit
Text Generation • 8B • Updated • 29 • 1 -
mlx-community/DeepSeek-R1-0528-Qwen3-8B-8bit
Text Generation • 2B • Updated • 1.09k • 1 -
mlx-community/DeepSeek-R1-0528-Qwen3-8B-bf16
Text Generation • 8B • Updated • 1.1k • • 2
Healthcare oriented LLM conversions to MLX
-
mlx-community/medgemma-4b-it-4bit
Image-Text-to-Text • 0.9B • Updated • 1.06k • 2 -
mlx-community/medgemma-4b-it-6bit
Image-Text-to-Text • 1B • Updated • 18 • 1 -
mlx-community/medgemma-4b-it-8bit
Image-Text-to-Text • 1B • Updated • 36 • 1 -
mlx-community/medgemma-4b-it-bf16
Image-Text-to-Text • 5B • Updated • 1.07k • 1
Nemotron MLX conversions I've done
-
mlx-community/AceReason-Nemotron-7B-4bit
Text Generation • 1B • Updated • 41 -
mlx-community/AceReason-Nemotron-7B-8bit
Text Generation • 2B • Updated • 7 -
mlx-community/AceReason-Nemotron-7B-bf16
Text Generation • 8B • Updated • 10 -
mlx-community/AceReason-Nemotron-1.1-7B-4bit
Text Generation • 1B • Updated • 17
TheDrummer MLX model conversions I've done
Abliterated model conversions to MLX
-
mlx-community/Josiefied-Health-Qwen3-8B-abliterated-v1-4bit
Text Generation • 1B • Updated • 29 -
mlx-community/Josiefied-Health-Qwen3-8B-abliterated-v1-8bit
Text Generation • 2B • Updated • 20 -
mlx-community/Josiefied-Health-Qwen3-8B-abliterated-v1-bf16
Text Generation • 8B • Updated • 33 • 1 -
mlx-community/Josiefied-DeepSeek-R1-0528-Qwen3-8B-abliterated-v1-4bit
Text Generation • 1B • Updated • 1.14k • 1