MLX quantized variants of nvidia/Nemotron-Cascade-2-30B-A3B (hybrid Mamba2 + Transformer + MoE, 30B/3B active)
Jorge Leon
leonsarmiento
AI & ML interests
AI for Environment
Recent Activity
updated a collection about 7 hours ago
Gemma 4 26B A4B MLX Quantizations updated a model about 7 hours ago
leonsarmiento/gemma-4-26B-A4B-it-2bit-XL-mlx published a model about 7 hours ago
leonsarmiento/gemma-4-26B-A4B-it-2bit-XL-mlxOrganizations
MLX quantizations of Agents-A1 (Qwen3.5 MoE, ~3B active). BaseQuant_XL variants.
Qwen3.6-35B-A3B MoE (35B/~3B active). Vanilla + Huihui-abliterated + heretic. BaseQuant_XL recommended.
-
leonsarmiento/Qwen3.6-35B-A3B-5bit-XL-mlx
Image-Text-to-Text • 7B • Updated • 120 -
leonsarmiento/Qwen3.6-35B-A3B-6bit-XL-mlx
Image-Text-to-Text • 8B • Updated • 75 -
leonsarmiento/Huihui-Qwen3.6-35B-A3B-abliterated-5bit-XL-mlx
Image-Text-to-Text • 7B • Updated • 307 -
leonsarmiento/Huihui-Qwen3.6-35B-A3B-abliterated-6bit-XL-mlx
Image-Text-to-Text • 8B • Updated • 190
MLX quantizations based on Nex-N2-mini (35B MoE, ~3B active, Qwen3.5). Includes vanilla and Huihui-abliterated variants. BaseQuant_XL recommended.
-
leonsarmiento/Nex-N2-mini-5bit-XL-mlx
Image-Text-to-Text • 7B • Updated • 71 -
leonsarmiento/Nex-N2-mini-6bit-XL-mlx
Image-Text-to-Text • 8B • Updated • 66 -
leonsarmiento/Nex-N2-mini-5bit-mlx
Image-Text-to-Text • 7B • Updated • 105 -
leonsarmiento/Huihui-Nex-N2-mini-abliterated-5bit-XL-mlx
Image-Text-to-Text • 7B • Updated • 129
MLX quantizations of zai-org/GLM-4.7-Flash (31B MoE, ~3B active). BaseQuant_XL recommended over standard variants.
DARE-TIES merge of Ornith-1.0-35B and Agents-A1 (Qwen3.5-35B-A3B MoE) — BaseQuant_XL MLX quantizations
-
leonsarmiento/Ornith-Agents-A1-3.6-35B-A3B-dare_ties-5bit-XL-mlx
Image-Text-to-Text • 7B • Updated • 460 -
leonsarmiento/Ornith-Agents-A1-3.6-35B-A3B-dare_ties-6bit-XL-mlx
Image-Text-to-Text • 8B • Updated • 846 • 1 -
leonsarmiento/Ornith-Agents-A1-3.6-35B-A3B-task_arithmetic_v2-5bit-XL-mlx
Image-Text-to-Text • 7B • Updated • 525 • 1 -
leonsarmiento/Ornith-Agents-A1-3.6-35B-A3B-task_arithmetic_v2-6bit-XL-mlx
Image-Text-to-Text • 8B • Updated • 489 • 1
MLX quantizations based on Qwen3.6-27B dense architecture. Includes vanilla and uncensored-heretic variants.
Ornith-1.0-35B MoE (35B/~3B active). Vanilla + uncensored-heretic. BaseQuant_XL recommended.
-
leonsarmiento/Ornith-1.0-35B-5bit-XL-mlx
Image-Text-to-Text • 7B • Updated • 3.3k • 10 -
leonsarmiento/Ornith-1.0-35B-6bit-XL-mlx
Image-Text-to-Text • 8B • Updated • 326 -
leonsarmiento/Ornith-1.0-35B-5bit-mlx
Image-Text-to-Text • 7B • Updated • 23.9k • 6 -
leonsarmiento/Ornith-1.0-35B-uncensored-heretic-5bit-XL-mlx
Image-Text-to-Text • 7B • Updated • 1.07k • 3
Gemma-4-26B-A4B QAT MoE (25.2B/3.8B active). Vanilla + Huihui-abliterated. BaseQuant_XL recommended.
MLX quantized variants of nvidia/Nemotron-Cascade-2-30B-A3B (hybrid Mamba2 + Transformer + MoE, 30B/3B active)
DARE-TIES merge of Ornith-1.0-35B and Agents-A1 (Qwen3.5-35B-A3B MoE) — BaseQuant_XL MLX quantizations
-
leonsarmiento/Ornith-Agents-A1-3.6-35B-A3B-dare_ties-5bit-XL-mlx
Image-Text-to-Text • 7B • Updated • 460 -
leonsarmiento/Ornith-Agents-A1-3.6-35B-A3B-dare_ties-6bit-XL-mlx
Image-Text-to-Text • 8B • Updated • 846 • 1 -
leonsarmiento/Ornith-Agents-A1-3.6-35B-A3B-task_arithmetic_v2-5bit-XL-mlx
Image-Text-to-Text • 7B • Updated • 525 • 1 -
leonsarmiento/Ornith-Agents-A1-3.6-35B-A3B-task_arithmetic_v2-6bit-XL-mlx
Image-Text-to-Text • 8B • Updated • 489 • 1
MLX quantizations of Agents-A1 (Qwen3.5 MoE, ~3B active). BaseQuant_XL variants.
MLX quantizations based on Qwen3.6-27B dense architecture. Includes vanilla and uncensored-heretic variants.
Qwen3.6-35B-A3B MoE (35B/~3B active). Vanilla + Huihui-abliterated + heretic. BaseQuant_XL recommended.
-
leonsarmiento/Qwen3.6-35B-A3B-5bit-XL-mlx
Image-Text-to-Text • 7B • Updated • 120 -
leonsarmiento/Qwen3.6-35B-A3B-6bit-XL-mlx
Image-Text-to-Text • 8B • Updated • 75 -
leonsarmiento/Huihui-Qwen3.6-35B-A3B-abliterated-5bit-XL-mlx
Image-Text-to-Text • 7B • Updated • 307 -
leonsarmiento/Huihui-Qwen3.6-35B-A3B-abliterated-6bit-XL-mlx
Image-Text-to-Text • 8B • Updated • 190
Ornith-1.0-35B MoE (35B/~3B active). Vanilla + uncensored-heretic. BaseQuant_XL recommended.
-
leonsarmiento/Ornith-1.0-35B-5bit-XL-mlx
Image-Text-to-Text • 7B • Updated • 3.3k • 10 -
leonsarmiento/Ornith-1.0-35B-6bit-XL-mlx
Image-Text-to-Text • 8B • Updated • 326 -
leonsarmiento/Ornith-1.0-35B-5bit-mlx
Image-Text-to-Text • 7B • Updated • 23.9k • 6 -
leonsarmiento/Ornith-1.0-35B-uncensored-heretic-5bit-XL-mlx
Image-Text-to-Text • 7B • Updated • 1.07k • 3
MLX quantizations based on Nex-N2-mini (35B MoE, ~3B active, Qwen3.5). Includes vanilla and Huihui-abliterated variants. BaseQuant_XL recommended.
-
leonsarmiento/Nex-N2-mini-5bit-XL-mlx
Image-Text-to-Text • 7B • Updated • 71 -
leonsarmiento/Nex-N2-mini-6bit-XL-mlx
Image-Text-to-Text • 8B • Updated • 66 -
leonsarmiento/Nex-N2-mini-5bit-mlx
Image-Text-to-Text • 7B • Updated • 105 -
leonsarmiento/Huihui-Nex-N2-mini-abliterated-5bit-XL-mlx
Image-Text-to-Text • 7B • Updated • 129
Gemma-4-26B-A4B QAT MoE (25.2B/3.8B active). Vanilla + Huihui-abliterated. BaseQuant_XL recommended.
MLX quantizations of zai-org/GLM-4.7-Flash (31B MoE, ~3B active). BaseQuant_XL recommended over standard variants.