3-bit VLM base + 4-bit MTP drafter. Pair both for accelerated instruct decode. reasoning_effort baked to low.
Jorge Leon
leonsarmiento
AI & ML interests
AI for Environment
Recent Activity
updated a model 2 days ago
leonsarmiento/Orion-26B-A4B-v1-6bit-XL-mlx published a model 2 days ago
leonsarmiento/Orion-26B-A4B-v1-6bit-XL-mlx updated a model 2 days ago
leonsarmiento/Tiger-Gemma-12B-v3-4bit-mlxOrganizations
Best local MLX-quantized LLMs fitting 48GB unified memory. 6-bit XL variants are data-agnostic honest kings; oQ4e-XL for RAM-desperate coders.
-
leonsarmiento/gemma-4-26B-A4B-it-6bit-XL-mlx
Image-Text-to-Text • 26B • Updated • 217 • 3 -
leonsarmiento/Qwen3.6-35B-A3B-6bit-XL-mlx
Image-Text-to-Text • 35B • Updated • 104 -
leonsarmiento/Qwen3.6-35B-A3B-oQ4e-mtp-XL-mlx
Image-Text-to-Text • 36B • Updated • 304 • 1 -
leonsarmiento/Ornith-1.0-35B-6bit-XL-mlx
Image-Text-to-Text • 35B • Updated • 90
3-bit VLM base + 4-bit MTP drafter. Pair both for accelerated instruct decode. reasoning_effort baked to low.
Best local MLX-quantized LLMs fitting 48GB unified memory. 6-bit XL variants are data-agnostic honest kings; oQ4e-XL for RAM-desperate coders.
-
leonsarmiento/gemma-4-26B-A4B-it-6bit-XL-mlx
Image-Text-to-Text • 26B • Updated • 217 • 3 -
leonsarmiento/Qwen3.6-35B-A3B-6bit-XL-mlx
Image-Text-to-Text • 35B • Updated • 104 -
leonsarmiento/Qwen3.6-35B-A3B-oQ4e-mtp-XL-mlx
Image-Text-to-Text • 36B • Updated • 304 • 1 -
leonsarmiento/Ornith-1.0-35B-6bit-XL-mlx
Image-Text-to-Text • 35B • Updated • 90
models 46
leonsarmiento/Orion-26B-A4B-v1-6bit-XL-mlx
Image-Text-to-Text • 26B • Updated • 37
leonsarmiento/Tiger-Gemma-12B-v3-4bit-mlx
13B • Updated • 34
leonsarmiento/Tiger-Gemma-12B-v3-8bit-mlx
13B • Updated • 13
leonsarmiento/L3-8B-Sunfall-v0.5-Stheno-v3.2-4bit-mlx
8B • Updated • 31
leonsarmiento/L3-8B-Sunfall-v0.5-Stheno-v3.2-8bit-mlx
8B • Updated • 16
leonsarmiento/GRM-3.2-Sky-6bit-XL-mlx
Image-Text-to-Text • 35B • Updated • 34
leonsarmiento/Ornith-1.5-35B-A3B-6bit-XL-mlx
Image-Text-to-Text • 35B • Updated • 508 • 1
leonsarmiento/Qwen3.8-27B-3bit-mtp-mlx
Image-Text-to-Text • 28B • Updated • 2.28k • 6
leonsarmiento/Qwen3.8-27B-3bit-mlx
Image-Text-to-Text • 27B • Updated • 1.08k • 1
leonsarmiento/Nemotron-3.5-Lightning-30B-A3B-6bit-XL-mlx
Text Generation • 32B • Updated • 399
datasets 0
None public yet