🤝 Open to Collab

Yinan Long

Brooooooklyn

4 1 7

anemll's profile picture

mycometg3's profile picture

thedarkstar's profile picture

https://github.com/Brooooooklyn

Brooooook_lyn
Brooooooklyn

AI & ML interests

None yet

Recent Activity

updated a model about 20 hours ago

Brooooooklyn/Qwen-AgentWorld-35B-A3B-mxfp4-mlx

updated a model about 22 hours ago

Brooooooklyn/Qwen-AgentWorld-35B-A3B-nvfp4-mlx

updated a model about 22 hours ago

Brooooooklyn/Ornith-1.0-35B-mxfp4-mlx

View all activity

Organizations

None yet

Brooooooklyn 's collections 8

Unsloth NVFP4 Tensor-Class Recipe for MLX — macOS + DGX

Unsloth dynamic quants for MLX: MXFP4+MXFP8 on macOS; NVFP4+E4M3 weights with A16 on DGX.

Brooooooklyn/Agents-A1-mxfp4-mlx

Text Generation • 35B • Updated about 24 hours ago • 29
Brooooooklyn/Agents-A1-nvfp4-mlx

Text Generation • 35B • Updated 1 day ago • 28
Brooooooklyn/Ornith-1.0-35B-mxfp4-mlx

Text Generation • 35B • Updated about 22 hours ago • 94 • 1
Brooooooklyn/Ornith-1.0-35B-nvfp4-mlx

Text Generation • 35B • Updated about 24 hours ago • 64

Qwen-AgentWorld-35B-A3B-unsloth-mlx

Qwen-AgentWorld-35B-A3B (Qwen3.5-VL-MoE world model) for Apple Silicon MLX: legacy imatrix-AWQ Q3–Q8 + MXFP8, quality-verified vs BF16.

Brooooooklyn/Qwen-AgentWorld-35B-A3B-UD-Q3_K_XL-mlx

Image-Text-to-Text • 35B • Updated Jul 3 • 60 • 1
Brooooooklyn/Qwen-AgentWorld-35B-A3B-UD-Q4_K_XL-mlx

Image-Text-to-Text • 35B • Updated Jul 3 • 46
Brooooooklyn/Qwen-AgentWorld-35B-A3B-UD-Q5_K_XL-mlx

Image-Text-to-Text • 35B • Updated Jul 3 • 50
Brooooooklyn/Qwen-AgentWorld-35B-A3B-UD-Q6_K_XL-mlx

Image-Text-to-Text • 35B • Updated Jul 3 • 18

Gemma-4-31B-IT-unsloth-mlx

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 • 31B • Updated May 16 • 20
Brooooooklyn/Gemma-4-31B-IT-UD-Q3_K_XL-mlx

Text Generation • 31B • Updated May 16 • 32
Brooooooklyn/Gemma-4-31B-IT-UD-Q4_K_XL-mlx

Text Generation • 31B • Updated May 16 • 50
Brooooooklyn/Gemma-4-31B-IT-UD-MXFP4_K_XL-mlx

Text Generation • 31B • Updated May 16 • 14 • 1

Qwen-3.6-unsloth-mlx

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 • 35B • Updated May 15 • 339 • 7
Brooooooklyn/Qwen3.6-35B-A3B-UD-Q3_K_XL-mlx

Text Generation • 35B • Updated May 15 • 415 • 4
Brooooooklyn/Qwen3.6-35B-A3B-UD-Q4_K_XL-mlx

Text Generation • 35B • Updated May 15 • 857 • 9
Brooooooklyn/Qwen3.6-35B-A3B-UD-Q5_K_XL-mlx

Text Generation • 35B • Updated May 15 • 158 • 2

NVIDIA NVFP4 → MLX

NVIDIA post-trained NVFP4 checkpoints (ModelOpt PTQ) transcoded to MLX for Apple Silicon / mlx-node, keeping NVIDIA's per-layer bit allocation.

Brooooooklyn/Gemma-4-26B-A4B-NVFP4-mlx

Text Generation • 26B • Updated Jul 5 • 48 • 1

Ornith-1.0-35B-unsloth-mlx

Ornith-1.0-35B for Apple Silicon MLX: legacy Unsloth Dynamic Q3–Q8 + MXFP8. Output quality verified vs BF16.

Brooooooklyn/Ornith-1.0-35B-UD-Q3_K_XL-mlx

Text Generation • 35B • Updated Jul 3 • 65
Brooooooklyn/Ornith-1.0-35B-UD-Q4_K_XL-mlx

Text Generation • 35B • Updated Jul 3 • 69
Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-mlx

Text Generation • 35B • Updated Jul 3 • 125 • 1
Brooooooklyn/Ornith-1.0-35B-UD-Q6_K_XL-mlx

Text Generation • 35B • Updated Jul 3 • 45 • 1

Gemma-4-26B-IT-unsloth-mlx

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 • 26B • Updated May 15 • 64
Brooooooklyn/Gemma-4-26B-A4B-IT-UD-MXFP4_K_XL-mlx

Text Generation • 26B • Updated May 15 • 35 • 1
Brooooooklyn/Gemma-4-26B-A4B-IT-UD-Q4_K_XL-mlx

Text Generation • 26B • Updated May 15 • 123
Brooooooklyn/Gemma-4-26B-A4B-IT-UD-NVFP4_K_XL-mlx

Text Generation • 26B • Updated May 15 • 24

Qwen-3.5-unsloth-mlx

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 • 9B • Updated Mar 24 • 477 • 13
Brooooooklyn/Qwen3.5-27B-unsloth-mlx

Text Generation • 27B • Updated Mar 24 • 558 • 18
Brooooooklyn/Qwen3.5-35B-A3B-UD-Q2_K_XL-mlx

Text Generation • 35B • Updated Mar 29 • 33
Brooooooklyn/Qwen3.5-35B-A3B-UD-Q3_K_XL-mlx

Text Generation • 35B • Updated Mar 29 • 65 • 2

Unsloth NVFP4 Tensor-Class Recipe for MLX — macOS + DGX

Unsloth dynamic quants for MLX: MXFP4+MXFP8 on macOS; NVFP4+E4M3 weights with A16 on DGX.

Brooooooklyn/Agents-A1-mxfp4-mlx

Text Generation • 35B • Updated about 24 hours ago • 29
Brooooooklyn/Agents-A1-nvfp4-mlx

Text Generation • 35B • Updated 1 day ago • 28
Brooooooklyn/Ornith-1.0-35B-mxfp4-mlx

Text Generation • 35B • Updated about 22 hours ago • 94 • 1
Brooooooklyn/Ornith-1.0-35B-nvfp4-mlx

Text Generation • 35B • Updated about 24 hours ago • 64

NVIDIA NVFP4 → MLX

NVIDIA post-trained NVFP4 checkpoints (ModelOpt PTQ) transcoded to MLX for Apple Silicon / mlx-node, keeping NVIDIA's per-layer bit allocation.

Brooooooklyn/Gemma-4-26B-A4B-NVFP4-mlx

Text Generation • 26B • Updated Jul 5 • 48 • 1

Qwen-AgentWorld-35B-A3B-unsloth-mlx

Qwen-AgentWorld-35B-A3B (Qwen3.5-VL-MoE world model) for Apple Silicon MLX: legacy imatrix-AWQ Q3–Q8 + MXFP8, quality-verified vs BF16.

Brooooooklyn/Qwen-AgentWorld-35B-A3B-UD-Q3_K_XL-mlx

Image-Text-to-Text • 35B • Updated Jul 3 • 60 • 1
Brooooooklyn/Qwen-AgentWorld-35B-A3B-UD-Q4_K_XL-mlx

Image-Text-to-Text • 35B • Updated Jul 3 • 46
Brooooooklyn/Qwen-AgentWorld-35B-A3B-UD-Q5_K_XL-mlx

Image-Text-to-Text • 35B • Updated Jul 3 • 50
Brooooooklyn/Qwen-AgentWorld-35B-A3B-UD-Q6_K_XL-mlx

Image-Text-to-Text • 35B • Updated Jul 3 • 18

Ornith-1.0-35B-unsloth-mlx

Ornith-1.0-35B for Apple Silicon MLX: legacy Unsloth Dynamic Q3–Q8 + MXFP8. Output quality verified vs BF16.

Brooooooklyn/Ornith-1.0-35B-UD-Q3_K_XL-mlx

Text Generation • 35B • Updated Jul 3 • 65
Brooooooklyn/Ornith-1.0-35B-UD-Q4_K_XL-mlx

Text Generation • 35B • Updated Jul 3 • 69
Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-mlx

Text Generation • 35B • Updated Jul 3 • 125 • 1
Brooooooklyn/Ornith-1.0-35B-UD-Q6_K_XL-mlx

Text Generation • 35B • Updated Jul 3 • 45 • 1

Gemma-4-31B-IT-unsloth-mlx

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 • 31B • Updated May 16 • 20
Brooooooklyn/Gemma-4-31B-IT-UD-Q3_K_XL-mlx

Text Generation • 31B • Updated May 16 • 32
Brooooooklyn/Gemma-4-31B-IT-UD-Q4_K_XL-mlx

Text Generation • 31B • Updated May 16 • 50
Brooooooklyn/Gemma-4-31B-IT-UD-MXFP4_K_XL-mlx

Text Generation • 31B • Updated May 16 • 14 • 1

Gemma-4-26B-IT-unsloth-mlx

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 • 26B • Updated May 15 • 64
Brooooooklyn/Gemma-4-26B-A4B-IT-UD-MXFP4_K_XL-mlx

Text Generation • 26B • Updated May 15 • 35 • 1
Brooooooklyn/Gemma-4-26B-A4B-IT-UD-Q4_K_XL-mlx

Text Generation • 26B • Updated May 15 • 123
Brooooooklyn/Gemma-4-26B-A4B-IT-UD-NVFP4_K_XL-mlx

Text Generation • 26B • Updated May 15 • 24

Qwen-3.6-unsloth-mlx

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 • 35B • Updated May 15 • 339 • 7
Brooooooklyn/Qwen3.6-35B-A3B-UD-Q3_K_XL-mlx

Text Generation • 35B • Updated May 15 • 415 • 4
Brooooooklyn/Qwen3.6-35B-A3B-UD-Q4_K_XL-mlx

Text Generation • 35B • Updated May 15 • 857 • 9
Brooooooklyn/Qwen3.6-35B-A3B-UD-Q5_K_XL-mlx

Text Generation • 35B • Updated May 15 • 158 • 2

Qwen-3.5-unsloth-mlx

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 • 9B • Updated Mar 24 • 477 • 13
Brooooooklyn/Qwen3.5-27B-unsloth-mlx

Text Generation • 27B • Updated Mar 24 • 558 • 18
Brooooooklyn/Qwen3.5-35B-A3B-UD-Q2_K_XL-mlx

Text Generation • 35B • Updated Mar 29 • 33
Brooooooklyn/Qwen3.5-35B-A3B-UD-Q3_K_XL-mlx

Text Generation • 35B • Updated Mar 29 • 65 • 2