baa.ai

company

https://baa.ai

black-sheep-ai-baa

Activity Feed

AI & ML interests

Model Quantization

Recent Activity

tomkay updated a model about 3 hours ago

baa-ai/Gemma-4-31B-it-RAM-29GB-MLX

tomkay updated a model about 3 hours ago

baa-ai/Gemma-4-31B-it-RAM-24GB-MLX

tomkay updated a model about 3 hours ago

baa-ai/Gemma-4-31B-it-RAM-4bit-MLX

View all activity

baa-ai 's collections 11

MiniMax-M2.7 (MLX)

RAM quantized versions of MiniMaxAI/MiniMax-M2.7 for Apple Silicon. Size points: 100 GB, 111 GB, 116 GB, 120 GB.

baa-ai/MiniMax-M2.7-RAM-100GB-MLX

Text Generation • 229B • Updated about 2 hours ago • 2.05k • 4
baa-ai/MiniMax-M2.7-RAM-120GB-MLX

Text Generation • 229B • Updated about 2 hours ago • 1.63k • 3
baa-ai/MiniMax-M2.7-RAM-116GB-MLX

Text Generation • 229B • Updated about 2 hours ago • 452 • 1
baa-ai/MiniMax-M2.7-RAM-111GB-MLX

Text Generation • 229B • Updated about 2 hours ago • 223 • 1

Nemotron 3 Super

MINT quantized Nemotron-3-Super-120B — hybrid Mamba-MoE-Attention (MLX & GGUF)

baa-ai/Nemotron-3-Super-120B-A12B-MINT-MLX

121B • Updated about 2 hours ago • 1.42k • 1
baa-ai/Nemotron-3-Super-120B-A12B-MINT-GGUF

121B • Updated about 2 hours ago • 224

GLM

Baa.ai quantized versions of GLM models

baa-ai/GLM-5-SWAN-5bit-MLX

744B • Updated about 2 hours ago • 1.36k
baa-ai/GLM-4.7-Flash-RAM-20GB-MLX

30B • Updated about 2 hours ago • 602
baa-ai/GLM-5.1-RAM-270GB-MLX

744B • Updated about 2 hours ago • 3.51k • 2
baa-ai/GLM-5.1-RAM-420GB-MLX

744B • Updated about 2 hours ago • 4.99k • 4

Llama 4

MINT & SWAN quantized versions of Llama 4 Scout and Maverick (MLX & GGUF)

baa-ai/Llama-4-Scout-17B-16E-Instruct-RAM-60GB-MLX

18B • Updated about 2 hours ago • 324
baa-ai/Llama-4-Maverick-17B-128E-Instruct-RAM-170GB-MLX

52B • Updated about 2 hours ago • 313

Qwen3.5-35B-A3B

MINT quantized versions of Qwen3.5-35B-A3B at multiple budget targets (MLX & GGUF)

baa-ai/Qwen3.5-35B-A3B-RAM-25GB-MLX

8B • Updated about 2 hours ago • 179
baa-ai/Qwen3.5-35B-A3B-RAM-29GB-MLX

9B • Updated about 2 hours ago • 162
baa-ai/Qwen3.5-35B-A3B-RAM-31GB-MLX

9B • Updated about 2 hours ago • 401

Qwen3.5-397B-A17B

MINT & SWAN quantized versions of Qwen3.5-397B-A17B (MLX & GGUF)

baa-ai/Qwen3.5-397B-A17B-RAM-220GB-MLX

61B • Updated about 2 hours ago • 201

Gemma 4

RAM optimised Gemma 4 models by baa.ai

baa-ai/Gemma-4-31B-it-RAM-30GB-MLX

9B • Updated about 2 hours ago • 3.61k • 2
baa-ai/Gemma-4-26B-A4B-it-RAM-20GB-MLX

7B • Updated about 2 hours ago • 1.72k • 4
baa-ai/Gemma-4-26B-A4B-it-RAM-14GB-MLX

5B • Updated about 2 hours ago • 1.43k • 5
baa-ai/Gemma-4-26B-A4B-it-RAM-18GB-MLX

6B • Updated about 2 hours ago • 485 • 1

MiniMax M2.5

MINT & SWAN quantized versions of MiniMax-M2.5 (MLX & GGUF)

baa-ai/MiniMax-M2.5-RAM-120GB-MLX

229B • Updated about 2 hours ago • 392

Llama 3

SWAN quantized versions of Llama 3.1 and 3.3 70B Instruct (MLX)

baa-ai/Llama-3.3-70B-Instruct-RAM-50GB-MLX

71B • Updated about 2 hours ago • 525 • 1
baa-ai/Llama-3.1-70B-Instruct-SWAN-5bit-MLX

71B • Updated about 2 hours ago • 418

Qwen3

MINT & SWAN quantized versions of Qwen3 models (MLX)

baa-ai/Qwen3-30B-A3B-RAM-20GB-MLX

31B • Updated about 2 hours ago • 89
baa-ai/Qwen3-8B-SWAN-6bit-MLX

8B • Updated about 2 hours ago • 107 • 1

Qwen3.5-122B-A10B

MINT quantized versions of Qwen3.5-122B-A10B at multiple budget targets (MLX & GGUF)

baa-ai/Qwen3.5-122B-A10B-RAM-48GB-MLX

15B • Updated about 2 hours ago • 3.87k • 6
baa-ai/Qwen3.5-122B-A10B-RAM-60GB-MLX

17B • Updated about 2 hours ago • 221
baa-ai/Qwen3.5-122B-A10B-RAM-100GB-MLX

28B • Updated about 2 hours ago • 240
baa-ai/Qwen3.5-122B-A10B-RAM-140GB-MLX

37B • Updated about 2 hours ago • 544

MiniMax-M2.7 (MLX)

RAM quantized versions of MiniMaxAI/MiniMax-M2.7 for Apple Silicon. Size points: 100 GB, 111 GB, 116 GB, 120 GB.

baa-ai/MiniMax-M2.7-RAM-100GB-MLX

Text Generation • 229B • Updated about 2 hours ago • 2.05k • 4
baa-ai/MiniMax-M2.7-RAM-120GB-MLX

Text Generation • 229B • Updated about 2 hours ago • 1.63k • 3
baa-ai/MiniMax-M2.7-RAM-116GB-MLX

Text Generation • 229B • Updated about 2 hours ago • 452 • 1
baa-ai/MiniMax-M2.7-RAM-111GB-MLX

Text Generation • 229B • Updated about 2 hours ago • 223 • 1

Gemma 4

RAM optimised Gemma 4 models by baa.ai

baa-ai/Gemma-4-31B-it-RAM-30GB-MLX

9B • Updated about 2 hours ago • 3.61k • 2
baa-ai/Gemma-4-26B-A4B-it-RAM-20GB-MLX

7B • Updated about 2 hours ago • 1.72k • 4
baa-ai/Gemma-4-26B-A4B-it-RAM-14GB-MLX

5B • Updated about 2 hours ago • 1.43k • 5
baa-ai/Gemma-4-26B-A4B-it-RAM-18GB-MLX

6B • Updated about 2 hours ago • 485 • 1

Nemotron 3 Super

MINT quantized Nemotron-3-Super-120B — hybrid Mamba-MoE-Attention (MLX & GGUF)

baa-ai/Nemotron-3-Super-120B-A12B-MINT-MLX

121B • Updated about 2 hours ago • 1.42k • 1
baa-ai/Nemotron-3-Super-120B-A12B-MINT-GGUF

121B • Updated about 2 hours ago • 224

MiniMax M2.5

MINT & SWAN quantized versions of MiniMax-M2.5 (MLX & GGUF)

baa-ai/MiniMax-M2.5-RAM-120GB-MLX

229B • Updated about 2 hours ago • 392

GLM

Baa.ai quantized versions of GLM models

baa-ai/GLM-5-SWAN-5bit-MLX

744B • Updated about 2 hours ago • 1.36k
baa-ai/GLM-4.7-Flash-RAM-20GB-MLX

30B • Updated about 2 hours ago • 602
baa-ai/GLM-5.1-RAM-270GB-MLX

744B • Updated about 2 hours ago • 3.51k • 2
baa-ai/GLM-5.1-RAM-420GB-MLX

744B • Updated about 2 hours ago • 4.99k • 4

Llama 3

SWAN quantized versions of Llama 3.1 and 3.3 70B Instruct (MLX)

baa-ai/Llama-3.3-70B-Instruct-RAM-50GB-MLX

71B • Updated about 2 hours ago • 525 • 1
baa-ai/Llama-3.1-70B-Instruct-SWAN-5bit-MLX

71B • Updated about 2 hours ago • 418

Llama 4

MINT & SWAN quantized versions of Llama 4 Scout and Maverick (MLX & GGUF)

baa-ai/Llama-4-Scout-17B-16E-Instruct-RAM-60GB-MLX

18B • Updated about 2 hours ago • 324
baa-ai/Llama-4-Maverick-17B-128E-Instruct-RAM-170GB-MLX

52B • Updated about 2 hours ago • 313

Qwen3

MINT & SWAN quantized versions of Qwen3 models (MLX)

baa-ai/Qwen3-30B-A3B-RAM-20GB-MLX

31B • Updated about 2 hours ago • 89
baa-ai/Qwen3-8B-SWAN-6bit-MLX

8B • Updated about 2 hours ago • 107 • 1

Qwen3.5-35B-A3B

MINT quantized versions of Qwen3.5-35B-A3B at multiple budget targets (MLX & GGUF)

baa-ai/Qwen3.5-35B-A3B-RAM-25GB-MLX

8B • Updated about 2 hours ago • 179
baa-ai/Qwen3.5-35B-A3B-RAM-29GB-MLX

9B • Updated about 2 hours ago • 162
baa-ai/Qwen3.5-35B-A3B-RAM-31GB-MLX

9B • Updated about 2 hours ago • 401

Qwen3.5-122B-A10B

MINT quantized versions of Qwen3.5-122B-A10B at multiple budget targets (MLX & GGUF)

baa-ai/Qwen3.5-122B-A10B-RAM-48GB-MLX

15B • Updated about 2 hours ago • 3.87k • 6
baa-ai/Qwen3.5-122B-A10B-RAM-60GB-MLX

17B • Updated about 2 hours ago • 221
baa-ai/Qwen3.5-122B-A10B-RAM-100GB-MLX

28B • Updated about 2 hours ago • 240
baa-ai/Qwen3.5-122B-A10B-RAM-140GB-MLX

37B • Updated about 2 hours ago • 544

Qwen3.5-397B-A17B

MINT & SWAN quantized versions of Qwen3.5-397B-A17B (MLX & GGUF)

baa-ai/Qwen3.5-397B-A17B-RAM-220GB-MLX

61B • Updated about 2 hours ago • 201

AI & ML interests

Recent Activity

Team members 1

baa-ai 's collections 11