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
new activity about 7 hours ago
scottlowry/Qwen3.8-27B-oQ4e-mtp:dude, this is one is finally working for me. thanks! liked a model about 8 hours ago
scottlowry/Qwen3.8-27B-oQ4e-mtp updated a model about 8 hours ago
leonsarmiento/Qwen3.8-27B-3bit-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 • 7B • Updated • 948 • 3 -
leonsarmiento/Qwen3.6-35B-A3B-6bit-XL-mlx
Image-Text-to-Text • 8B • Updated • 297 -
leonsarmiento/Qwen3.6-35B-A3B-oQ4e-mtp-XL-mlx
Image-Text-to-Text • 7B • Updated • 773 • 1 -
leonsarmiento/Ornith-1.0-35B-6bit-XL-mlx
Image-Text-to-Text • 8B • Updated • 395
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 • 7B • Updated • 948 • 3 -
leonsarmiento/Qwen3.6-35B-A3B-6bit-XL-mlx
Image-Text-to-Text • 8B • Updated • 297 -
leonsarmiento/Qwen3.6-35B-A3B-oQ4e-mtp-XL-mlx
Image-Text-to-Text • 7B • Updated • 773 • 1 -
leonsarmiento/Ornith-1.0-35B-6bit-XL-mlx
Image-Text-to-Text • 8B • Updated • 395
models 39
leonsarmiento/Qwen3.8-27B-3bit-mlx
Image-Text-to-Text • 4B • Updated
leonsarmiento/Qwen3.8-27B-MTP-4bit-mlx
Image-Text-to-Text • 66.4M • Updated
leonsarmiento/Nemotron-3.5-Lightning-30B-A3B-6bit-XL-mlx
Text Generation • 8B • Updated • 306
leonsarmiento/Qwen-AgentWorld-35B-A3B-6bit-XL-mlx
Text Generation • 8B • Updated • 89
leonsarmiento/gemma-4-12B-it-6bit-XL-mlx
Image-Text-to-Text • 3B • Updated • 105
leonsarmiento/Qwen3.6-35B-A3B-oQ4e-mtp-XL-mlx
Image-Text-to-Text • 7B • Updated • 773 • 1
leonsarmiento/Huihui-Nex-N2-mini-abliterated-5bit-XL-mlx
Image-Text-to-Text • 7B • Updated • 252
leonsarmiento/Nex-N2-mini-6bit-XL-mlx
Image-Text-to-Text • 8B • Updated • 61
leonsarmiento/GLM-4.7-Flash-6bit-XL-mlx
Text Generation • 7B • Updated • 823 • 1
leonsarmiento/Laguna-XS-2.1-6bit-XL-mlx
Text Generation • 8B • Updated • 719 • 1
datasets 0
None public yet