Jorge Leon

leonsarmiento's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated 2 collections 4 days ago

Local SOTA for 48GB Macs

Collection

Best local MLX-quantized LLMs fitting 48GB unified memory. 6-bit XL variants are data-agnostic honest kings; oQ4e-XL for RAM-desperate coders. • 9 items • Updated 4 days ago • 2

Ornith-35B-A3B

Collection

Ornith-1.0-35B MoE (35B/~3B active). Vanilla + uncensored-heretic. BaseQuant_XL recommended. • 8 items • Updated 4 days ago

updated a model 4 days ago

leonsarmiento/GRM-3.2-Sky-6bit-XL-mlx

Image-Text-to-Text • 8B • Updated 4 days ago • 14

published a model 4 days ago

leonsarmiento/GRM-3.2-Sky-6bit-XL-mlx

Image-Text-to-Text • 8B • Updated 4 days ago • 14

New activity in Qwen/Qwen3.8-27B 4 days ago

🙏 The community needs Qwen 3.8 35B-A3B models and others, help us get there 🚀

➕❤️ 154

19

#120 opened 12 days ago by

highpolygonal

New activity in ornith-ai/Ornith-1.5-35B-A3B 6 days ago

It’s Ornith 2.0 going to be built on top of Qwen3.6?

🔥👍 4

#24 opened 6 days ago by

leonsarmiento

liked 2 models 6 days ago

openai/gpt-oss-safeguard-20b

Text Generation • 22B • Updated Jan 14 • 79.7k • • 255

openai/gpt-oss-20b

Text Generation • 21B • Updated Aug 26, 2025 • 6.35M • • 4.96k

updated a model 9 days ago

leonsarmiento/Ornith-1.5-35B-A3B-6bit-XL-mlx

Image-Text-to-Text • 8B • Updated 9 days ago • 342 • 1

updated 2 collections 9 days ago

Ornith-35B-A3B

Collection

Ornith-1.0-35B MoE (35B/~3B active). Vanilla + uncensored-heretic. BaseQuant_XL recommended. • 8 items • Updated 4 days ago

Local SOTA for 48GB Macs

Collection

Best local MLX-quantized LLMs fitting 48GB unified memory. 6-bit XL variants are data-agnostic honest kings; oQ4e-XL for RAM-desperate coders. • 9 items • Updated 4 days ago • 2

published a model 9 days ago

leonsarmiento/Ornith-1.5-35B-A3B-6bit-XL-mlx

Image-Text-to-Text • 8B • Updated 9 days ago • 342 • 1

liked 3 models 9 days ago

ornith-ai/Ornith-1.5-35B-A3B-MLX-6bit

Text Generation • 8B • Updated 9 days ago • 42.9k • 6

ornith-ai/Ornith-1.5-35B-A3B-MLX

Text Generation • 35B • Updated 9 days ago • 90.5k • 47

ornith-ai/Ornith-1.5-35B-A3B

Text Generation • 36B • Updated 6 days ago • 88.1k • 486

updated a model 11 days ago

leonsarmiento/Qwen3.8-27B-3bit-mtp-mlx

Image-Text-to-Text • 4B • Updated 11 days ago • 1.13k • 5

updated a collection 11 days ago

Qwen3.8-27B MLX Quantizations

Collection

3-bit VLM base + 4-bit MTP drafter. Pair both for accelerated instruct decode. reasoning_effort baked to low. • 2 items • Updated 11 days ago

published a model 11 days ago

leonsarmiento/Qwen3.8-27B-3bit-mtp-mlx

Image-Text-to-Text • 4B • Updated 11 days ago • 1.13k • 5

updated a model 11 days ago

leonsarmiento/Qwen3.8-27B-3bit-mlx

Image-Text-to-Text • 4B • Updated 11 days ago • 616 • 1

New activity in scottlowry/Qwen3.8-27B-oQ4e-mtp 11 days ago

dude, this is one is finally working for me. thanks!

👍 2

#1 opened 11 days ago by

leonsarmiento