NVIDIA post-trained NVFP4 checkpoints (ModelOpt PTQ) transcoded to MLX for Apple Silicon / mlx-node, keeping NVIDIA's per-layer bit allocation.
🤝 Open to Collab
Yinan Long
Brooooooklyn
AI & ML interests
None yet
Recent Activity
updated a collection 13 days ago
NVIDIA NVFP4 → MLX updated a model 14 days ago
Brooooooklyn/Gemma-4-26B-A4B-NVFP4-mlx published a model 14 days ago
Brooooooklyn/Gemma-4-26B-A4B-NVFP4-mlxOrganizations
None yet
Ornith-1.0-35B for Apple Silicon MLX: Unsloth-dynamic Q3–Q8 + MXFP8/MXFP4/NVFP4. Output quality verified vs BF16.
-
Brooooooklyn/Ornith-1.0-35B-UD-Q3_K_XL-mlx
Text Generation • 5B • Updated • 598 -
Brooooooklyn/Ornith-1.0-35B-UD-Q4_K_XL-mlx
Text Generation • 6B • Updated • 577 -
Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-mlx
Text Generation • 8B • Updated • 342 -
Brooooooklyn/Ornith-1.0-35B-UD-Q6_K_XL-mlx
Text Generation • 9B • Updated • 801 • 1
Gemma-4-26B-A4B-IT MoE quantized for Apple Silicon (MLX) — Unsloth Dynamic 2.0 with AWQ imatrix pre-scaling.
-
Brooooooklyn/Gemma-4-26B-A4B-IT-UD-Q3_K_XL-mlx
Text Generation • 4B • Updated • 130 -
Brooooooklyn/Gemma-4-26B-A4B-IT-UD-MXFP4_K_XL-mlx
Text Generation • 6B • Updated • 48 • 1 -
Brooooooklyn/Gemma-4-26B-A4B-IT-UD-Q4_K_XL-mlx
Text Generation • 5B • Updated • 189 -
Brooooooklyn/Gemma-4-26B-A4B-IT-UD-NVFP4_K_XL-mlx
Text Generation • 7B • Updated • 19
AWQ-style pre-scaling using Unsloth's imatrix calibration data, then 3-6-bit affine quantization with the Unsloth mixed-precision recipe via MLX
-
Brooooooklyn/Qwen3.5-9B-unsloth-mlx
Text Generation • 2B • Updated • 726 • 12 -
Brooooooklyn/Qwen3.5-27B-unsloth-mlx
Text Generation • 6B • Updated • 760 • 18 -
Brooooooklyn/Qwen3.5-35B-A3B-UD-Q2_K_XL-mlx
Text Generation • 4B • Updated • 46 -
Brooooooklyn/Qwen3.5-35B-A3B-UD-Q3_K_XL-mlx
Text Generation • 6B • Updated • 42 • 2
Qwen-AgentWorld-35B-A3B (Qwen3.5-VL-MoE world model) for Apple Silicon MLX: imatrix-AWQ Q3–Q8 + MXFP4/8 + NVFP4, quality-verified vs BF16.
-
Brooooooklyn/Qwen-AgentWorld-35B-A3B-UD-Q3_K_XL-mlx
Image-Text-to-Text • 5B • Updated • 231 • 1 -
Brooooooklyn/Qwen-AgentWorld-35B-A3B-UD-Q4_K_XL-mlx
Image-Text-to-Text • 6B • Updated • 310 -
Brooooooklyn/Qwen-AgentWorld-35B-A3B-UD-Q5_K_XL-mlx
Image-Text-to-Text • 7B • Updated • 272 -
Brooooooklyn/Qwen-AgentWorld-35B-A3B-UD-Q6_K_XL-mlx
Image-Text-to-Text • 8B • Updated • 304
Gemma-4-31B-IT (dense vision-language) quantized for Apple Silicon (MLX) — Unsloth Dynamic 2.0 with AWQ imatrix pre-scaling.
-
Brooooooklyn/Gemma-4-31B-IT-UD-Q2_K_XL-mlx
Text Generation • 7B • Updated • 37 -
Brooooooklyn/Gemma-4-31B-IT-UD-Q3_K_XL-mlx
Text Generation • 8B • Updated • 34 -
Brooooooklyn/Gemma-4-31B-IT-UD-Q4_K_XL-mlx
Text Generation • 9B • Updated • 103 -
Brooooooklyn/Gemma-4-31B-IT-UD-MXFP4_K_XL-mlx
Text Generation • 9B • Updated • 21 • 1
AWQ-style pre-scaling using Unsloth's imatrix calibration data, then 3-6-bit affine quantization with the Unsloth mixed-precision recipe via MLX
-
Brooooooklyn/Qwen3.6-35B-A3B-UD-Q2_K_XL-mlx
Text Generation • 4B • Updated • 647 • 7 -
Brooooooklyn/Qwen3.6-35B-A3B-UD-Q3_K_XL-mlx
Text Generation • 6B • Updated • 330 • 4 -
Brooooooklyn/Qwen3.6-35B-A3B-UD-Q4_K_XL-mlx
Text Generation • 7B • Updated • 1.45k • 9 -
Brooooooklyn/Qwen3.6-35B-A3B-UD-Q5_K_XL-mlx
Text Generation • 8B • Updated • 232 • 2
NVIDIA post-trained NVFP4 checkpoints (ModelOpt PTQ) transcoded to MLX for Apple Silicon / mlx-node, keeping NVIDIA's per-layer bit allocation.
Qwen-AgentWorld-35B-A3B (Qwen3.5-VL-MoE world model) for Apple Silicon MLX: imatrix-AWQ Q3–Q8 + MXFP4/8 + NVFP4, quality-verified vs BF16.
-
Brooooooklyn/Qwen-AgentWorld-35B-A3B-UD-Q3_K_XL-mlx
Image-Text-to-Text • 5B • Updated • 231 • 1 -
Brooooooklyn/Qwen-AgentWorld-35B-A3B-UD-Q4_K_XL-mlx
Image-Text-to-Text • 6B • Updated • 310 -
Brooooooklyn/Qwen-AgentWorld-35B-A3B-UD-Q5_K_XL-mlx
Image-Text-to-Text • 7B • Updated • 272 -
Brooooooklyn/Qwen-AgentWorld-35B-A3B-UD-Q6_K_XL-mlx
Image-Text-to-Text • 8B • Updated • 304
Ornith-1.0-35B for Apple Silicon MLX: Unsloth-dynamic Q3–Q8 + MXFP8/MXFP4/NVFP4. Output quality verified vs BF16.
-
Brooooooklyn/Ornith-1.0-35B-UD-Q3_K_XL-mlx
Text Generation • 5B • Updated • 598 -
Brooooooklyn/Ornith-1.0-35B-UD-Q4_K_XL-mlx
Text Generation • 6B • Updated • 577 -
Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-mlx
Text Generation • 8B • Updated • 342 -
Brooooooklyn/Ornith-1.0-35B-UD-Q6_K_XL-mlx
Text Generation • 9B • Updated • 801 • 1
Gemma-4-31B-IT (dense vision-language) quantized for Apple Silicon (MLX) — Unsloth Dynamic 2.0 with AWQ imatrix pre-scaling.
-
Brooooooklyn/Gemma-4-31B-IT-UD-Q2_K_XL-mlx
Text Generation • 7B • Updated • 37 -
Brooooooklyn/Gemma-4-31B-IT-UD-Q3_K_XL-mlx
Text Generation • 8B • Updated • 34 -
Brooooooklyn/Gemma-4-31B-IT-UD-Q4_K_XL-mlx
Text Generation • 9B • Updated • 103 -
Brooooooklyn/Gemma-4-31B-IT-UD-MXFP4_K_XL-mlx
Text Generation • 9B • Updated • 21 • 1
Gemma-4-26B-A4B-IT MoE quantized for Apple Silicon (MLX) — Unsloth Dynamic 2.0 with AWQ imatrix pre-scaling.
-
Brooooooklyn/Gemma-4-26B-A4B-IT-UD-Q3_K_XL-mlx
Text Generation • 4B • Updated • 130 -
Brooooooklyn/Gemma-4-26B-A4B-IT-UD-MXFP4_K_XL-mlx
Text Generation • 6B • Updated • 48 • 1 -
Brooooooklyn/Gemma-4-26B-A4B-IT-UD-Q4_K_XL-mlx
Text Generation • 5B • Updated • 189 -
Brooooooklyn/Gemma-4-26B-A4B-IT-UD-NVFP4_K_XL-mlx
Text Generation • 7B • Updated • 19
AWQ-style pre-scaling using Unsloth's imatrix calibration data, then 3-6-bit affine quantization with the Unsloth mixed-precision recipe via MLX
-
Brooooooklyn/Qwen3.6-35B-A3B-UD-Q2_K_XL-mlx
Text Generation • 4B • Updated • 647 • 7 -
Brooooooklyn/Qwen3.6-35B-A3B-UD-Q3_K_XL-mlx
Text Generation • 6B • Updated • 330 • 4 -
Brooooooklyn/Qwen3.6-35B-A3B-UD-Q4_K_XL-mlx
Text Generation • 7B • Updated • 1.45k • 9 -
Brooooooklyn/Qwen3.6-35B-A3B-UD-Q5_K_XL-mlx
Text Generation • 8B • Updated • 232 • 2
AWQ-style pre-scaling using Unsloth's imatrix calibration data, then 3-6-bit affine quantization with the Unsloth mixed-precision recipe via MLX
-
Brooooooklyn/Qwen3.5-9B-unsloth-mlx
Text Generation • 2B • Updated • 726 • 12 -
Brooooooklyn/Qwen3.5-27B-unsloth-mlx
Text Generation • 6B • Updated • 760 • 18 -
Brooooooklyn/Qwen3.5-35B-A3B-UD-Q2_K_XL-mlx
Text Generation • 4B • Updated • 46 -
Brooooooklyn/Qwen3.5-35B-A3B-UD-Q3_K_XL-mlx
Text Generation • 6B • Updated • 42 • 2