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 1 day ago
ornith-ai/Ornith-1.5-35B-A3B:It’s Ornith 2.0 going to be built on top of Qwen3.6? liked a model 1 day ago
openai/gpt-oss-safeguard-20b liked a model 1 day ago
openai/gpt-oss-20bOrganizations
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 • 522 • 3 -
leonsarmiento/Qwen3.6-35B-A3B-6bit-XL-mlx
Image-Text-to-Text • 8B • Updated • 148 -
leonsarmiento/Qwen3.6-35B-A3B-oQ4e-mtp-XL-mlx
Image-Text-to-Text • 7B • Updated • 546 • 1 -
leonsarmiento/Ornith-1.0-35B-6bit-XL-mlx
Image-Text-to-Text • 8B • Updated • 180
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 • 522 • 3 -
leonsarmiento/Qwen3.6-35B-A3B-6bit-XL-mlx
Image-Text-to-Text • 8B • Updated • 148 -
leonsarmiento/Qwen3.6-35B-A3B-oQ4e-mtp-XL-mlx
Image-Text-to-Text • 7B • Updated • 546 • 1 -
leonsarmiento/Ornith-1.0-35B-6bit-XL-mlx
Image-Text-to-Text • 8B • Updated • 180
models 40
leonsarmiento/Ornith-1.5-35B-A3B-6bit-XL-mlx
Image-Text-to-Text • 8B • Updated • 291
leonsarmiento/Qwen3.8-27B-3bit-mtp-mlx
Image-Text-to-Text • 4B • Updated • 845 • 3
leonsarmiento/Qwen3.8-27B-3bit-mlx
Image-Text-to-Text • 4B • Updated • 466 • 1
leonsarmiento/Nemotron-3.5-Lightning-30B-A3B-6bit-XL-mlx
Text Generation • 8B • Updated • 352
leonsarmiento/Qwen-AgentWorld-35B-A3B-6bit-XL-mlx
Text Generation • 8B • Updated • 110
leonsarmiento/gemma-4-12B-it-6bit-XL-mlx
Image-Text-to-Text • 3B • Updated • 119
leonsarmiento/Qwen3.6-35B-A3B-oQ4e-mtp-XL-mlx
Image-Text-to-Text • 7B • Updated • 546 • 1
leonsarmiento/Huihui-Nex-N2-mini-abliterated-5bit-XL-mlx
Image-Text-to-Text • 7B • Updated • 215
leonsarmiento/Nex-N2-mini-6bit-XL-mlx
Image-Text-to-Text • 8B • Updated • 46
leonsarmiento/GLM-4.7-Flash-6bit-XL-mlx
Text Generation • 7B • Updated • 733 • 1
datasets 0
None public yet