🤝 Open to Collab

Pipenetwork PRO

pipenetwork

markwoo2033's profile picture

TheOlRazzleDazzle's profile picture

jungletsubasa's profile picture

https://pipe.network

pipenetwork

AI & ML interests

AI & ML

Recent Activity

updated a collection 4 days ago

MiniMax-H3 MLX

updated a model 4 days ago

pipenetwork/MiniMax-H3-MLX-f32

published a model 4 days ago

pipenetwork/MiniMax-H3-MLX-f32

View all activity

Organizations

None yet

pipenetwork 's collections 18

MiniMax-H3 MLX

Apple Silicon (MLX) builds of MiniMax-H3, the 33B joint video+audio diffusion transformer. Code: github.com/PipeNetwork/minimax-h3-mlx

pipenetwork/MiniMax-H3-MLX-8bit

Image-Text-to-Video • 9B • Updated 4 days ago • 630 • 5
pipenetwork/MiniMax-H3-MLX-6bit

Image-Text-to-Video • 8B • Updated 4 days ago • 309 • 2
pipenetwork/MiniMax-H3-MLX-4bit

Image-Text-to-Video • 7B • Updated 4 days ago • 509 • 1
pipenetwork/MiniMax-H3-MLX-bf16

Image-Text-to-Video • 33B • Updated 4 days ago • 373 • 3

Inkling · MLX

975B-A41B multimodal MoE on Apple Silicon. Text+image+audio. Ported from scratch: github.com/PipeNetwork/inkling-mlx

pipenetwork/Inkling-MLX-8bit

Image-Text-to-Text • 266B • Updated 22 days ago • 716
pipenetwork/Inkling-MLX-6bit

Image-Text-to-Text • 207B • Updated 22 days ago • 844 • 1
pipenetwork/Inkling-MLX-4bit

Image-Text-to-Text • 148B • Updated 22 days ago • 1.11k • 1
pipenetwork/Inkling-MLX-REAP12-4bit

Image-Text-to-Text • 131B • Updated 22 days ago • 464

Nemotron TwoTower · MLX

NVIDIA Nemotron TwoTower 30B-A3B diffusion LM in MLX for Apple Silicon: AR tower + two-tower diffusion, 4/6/8-bit + bf16.

pipenetwork/Nemotron-3-Nano-30B-A3B-context-mlx-4bit

Text Generation • 32B • Updated Jul 2 • 73
pipenetwork/Nemotron-3-Nano-30B-A3B-context-mlx-6bit

Text Generation • 32B • Updated Jul 2 • 100 • 1
pipenetwork/Nemotron-3-Nano-30B-A3B-context-mlx-8bit

Text Generation • 32B • Updated Jul 2 • 67
pipenetwork/Nemotron-3-Nano-30B-A3B-context-mlx-bf16

Text Generation • 32B • Updated Jul 2 • 123

Ornith-1.0-397B — MLX

MLX (Apple Silicon) conversions of deepreinforce-ai/Ornith-1.0-397B (Qwen3.5-MoE, text-only). 4/6/8-bit and bf16.

pipenetwork/Ornith-1.0-397B-mlx-4bit

Text Generation • 396B • Updated Jun 26 • 714 • 3
pipenetwork/Ornith-1.0-397B-mlx-6bit

Text Generation • 396B • Updated Jun 26 • 180
pipenetwork/Ornith-1.0-397B-mlx-8bit

Text Generation • 396B • Updated Jun 26 • 399 • 3

GLM-5.2 MLX

First MLX builds of zai-org/GLM-5.2 (glm_moe_dsa MoE): 4/5/6/8-bit + a 512GB-friendly mixed.

pipenetwork/GLM-5.2-MLX-mixed-3_6bit

Text Generation • 743B • Updated Jun 17 • 6.04k • 6
pipenetwork/GLM-5.2-MLX-4bit

Text Generation • 743B • Updated Jun 17 • 1.44k • 3
pipenetwork/GLM-5.2-MLX-5bit

Text Generation • 743B • Updated Jun 17 • 462
pipenetwork/GLM-5.2-MLX-6bit

Text Generation • 743B • Updated Jun 17 • 495

Rio-3.1-Open-30B MLX

First MLX (Apple Silicon) quantizations of prefeitura-rio/Rio-3.1-Open-30B (Qwen3-MoE): 4/5/6/8-bit.

pipenetwork/Rio-3.1-Open-30B-MLX-8bit

Text Generation • 31B • Updated Jun 15 • 19
pipenetwork/Rio-3.1-Open-30B-MLX-6bit

Text Generation • 31B • Updated Jun 15 • 8
pipenetwork/Rio-3.1-Open-30B-MLX-5bit

Text Generation • 31B • Updated Jun 15 • 7
pipenetwork/Rio-3.1-Open-30B-MLX-4bit

Text Generation • 31B • Updated Jun 15 • 28

Gemma-4-31B-it MLX

MLX (Apple Silicon) quantizations of google/gemma-4-31B-it: 4/5/6/8-bit. Text-only.

pipenetwork/Gemma-4-31B-it-MLX-8bit

Text Generation • 31B • Updated Jun 13 • 20
pipenetwork/Gemma-4-31B-it-MLX-6bit

Text Generation • 31B • Updated Jun 13 • 12
pipenetwork/Gemma-4-31B-it-MLX-5bit

Text Generation • 31B • Updated Jun 13 • 7
pipenetwork/Gemma-4-31B-it-MLX-4bit

Text Generation • 31B • Updated Jun 13 • 18

MiniMax-M3 MLX

MLX (Apple Silicon) text-only conversions of MiniMax-M3 (427B MoE): 3-bit to 8-bit plus a mixed-precision build.

pipenetwork/MiniMax-M3-MLX-8bit

Text Generation • 426B • Updated Jun 13 • 384 • 1
pipenetwork/MiniMax-M3-MLX-6bit

Text Generation • 426B • Updated Jun 13 • 286
pipenetwork/MiniMax-M3-MLX-4bit

Text Generation • 426B • Updated Jun 13 • 306
pipenetwork/MiniMax-M3-MLX-mixed-3_6bit

Text Generation • 426B • Updated Jun 13 • 518 • 2

Frog (SWE/debugging) MLX

MLX quants of Microsoft's FrogBoss-32B & FrogMini-14B (Qwen3 debugging finetunes, SWE-bench ~45% pass@1) for Apple Silicon.

pipenetwork/FrogMini-14B-2510-MLX-4bit

Text Generation • 15B • Updated Jun 5 • 12
pipenetwork/FrogMini-14B-2510-MLX-8bit

Text Generation • 15B • Updated Jun 5 • 12
pipenetwork/FrogBoss-32B-2510-MLX-4bit

Text Generation • 33B • Updated Jun 5 • 9
pipenetwork/FrogBoss-32B-2510-MLX-8bit

Text Generation • 33B • Updated Jun 5 • 9

Inkling-Small · MLX

276B-A12B multimodal MoE on Apple Silicon. Same code path as Inkling 975B. REAP-25 is free: github.com/PipeNetwork/inkling-mlx

pipenetwork/Inkling-Small-MLX-8bit

Image-Text-to-Text • 74B • Updated 8 days ago • 150
pipenetwork/Inkling-Small-MLX-6bit

Image-Text-to-Text • 58B • Updated 8 days ago • 134
pipenetwork/Inkling-Small-MLX-4bit

Image-Text-to-Text • 41B • Updated 8 days ago • 345 • 1
pipenetwork/Inkling-Small-MLX-REAP25-4bit

Image-Text-to-Text • 31B • Updated 8 days ago • 286 • 1

DeepSeek-V4-Flash · MLX

304B MoE on Apple Silicon. deepseek_v4 is in no released runtime — ported from scratch. Take mixed-4_8bit. github.com/PipeNetwork/deepseek-v4-mlx

pipenetwork/DeepSeek-V4-Flash-MLX-8bit

Text Generation • 81B • Updated 7 days ago • 440
pipenetwork/DeepSeek-V4-Flash-MLX-6bit

Text Generation • 64B • Updated 7 days ago • 297
pipenetwork/DeepSeek-V4-Flash-MLX-mixed-4_8bit

Text Generation • 47B • Updated 7 days ago • 558 • 1
pipenetwork/DeepSeek-V4-Flash-MLX-4bit

Text Generation • 46B • Updated 7 days ago • 472

Qwen3.6-35B-A3B — MLX

MLX (Apple Silicon) conversion of Qwen/Qwen3.6-35B-A3B in NVFP4 — the MLX analog of nvidia/Qwen3.6-35B-A3B-NVFP4. Text-only.

pipenetwork/Qwen3.6-35B-A3B-mlx-nvfp4

Text Generation • 35B • Updated Jun 26 • 75

GLM-5.2 REAP (expert-pruned)

REAP expert-pruned GLM-5.2 (smaller/faster). REAP-25 near-lossless (+2.3% PPL); REAP-37 +7.3%; REAP-50 smallest but +37.5%.

pipenetwork/GLM-5.2-REAP25-MLX-4bit

Text Generation • 562B • Updated Jun 18 • 847 • 2
pipenetwork/GLM-5.2-REAP37-MLX-4bit

Text Generation • 472B • Updated Jun 18 • 654 • 1
pipenetwork/GLM-5.2-REAP50-MLX-4bit

Text Generation • 381B • Updated Jun 18 • 1.23k • 4

VISTA MLX

First MLX (Apple Silicon) quantizations of inclusionAI VISTA-9B and VISTA-4B (qwen3_5).

pipenetwork/VISTA-9B-MLX-8bit

Text Generation • 9B • Updated Jun 16 • 4
pipenetwork/VISTA-9B-MLX-6bit

Text Generation • 9B • Updated Jun 16 • 5
pipenetwork/VISTA-9B-MLX-5bit

Text Generation • 9B • Updated Jun 16 • 4
pipenetwork/VISTA-9B-MLX-4bit

Text Generation • 1B • Updated Jun 16 • 4

Gemma-4-26B-A4B-it MLX

MLX quantizations of google/gemma-4-26B-A4B-it (MoE): 5/6/8-bit (4-bit available from mlx-community). Text-only.

pipenetwork/Gemma-4-26B-A4B-it-MLX-8bit

Text Generation • 25B • Updated Jun 14 • 6
pipenetwork/Gemma-4-26B-A4B-it-MLX-6bit

Text Generation • 25B • Updated Jun 14 • 9
pipenetwork/Gemma-4-26B-A4B-it-MLX-5bit

Text Generation • 25B • Updated Jun 14 • 25

Kimi-K2.7-Code MLX

MLX build of Kimi-K2.7-Code. Base is natively 4-bit (int4 experts + bf16 rest); this keeps experts at 4-bit and lifts non-expert layers to 6-bit.

pipenetwork/Kimi-K2.7-Code-MLX-4bit-hiprec

Text Generation • 1T • Updated Jun 13 • 1.34k • 1

Holo-3.1 MLX (computer-use)

First working MLX builds of H Company's Holo-3.1 vision-language computer-use agents (Qwen3.5-VL). Vision-validated. Apache-2.0.

pipenetwork/Holo-3.1-4B-MLX-4bit

Image-Text-to-Text • 1.0B • Updated Jun 5 • 174 • 3
pipenetwork/Holo-3.1-4B-MLX-8bit

Image-Text-to-Text • 2B • Updated Jun 5 • 39 • 1
pipenetwork/Holo-3.1-9B-MLX-4bit

Image-Text-to-Text • 2B • Updated Jun 5 • 94
pipenetwork/Holo-3.1-9B-MLX-8bit

Image-Text-to-Text • 3B • Updated Jun 5 • 82 • 1

Nemotron-3 MLX (Apple Silicon)

MLX quants of NVIDIA Nemotron-3 for Apple Silicon: Ultra 550B (4/5/6/8-bit) and dense Nano-4B (4/8-bit), converted with mlx-lm.

pipenetwork/NVIDIA-Nemotron-3-Ultra-550B-A55B-MLX-4bit

Text Generation • 549B • Updated Jun 5 • 110
pipenetwork/NVIDIA-Nemotron-3-Ultra-550B-A55B-MLX-8bit

Text Generation • 549B • Updated Jun 5 • 83
pipenetwork/NVIDIA-Nemotron-3-Nano-4B-MLX-8bit

1B • Updated Jun 5 • 8
pipenetwork/NVIDIA-Nemotron-3-Nano-4B-MLX-4bit

0.6B • Updated Jun 5 • 6

MiniMax-H3 MLX

Apple Silicon (MLX) builds of MiniMax-H3, the 33B joint video+audio diffusion transformer. Code: github.com/PipeNetwork/minimax-h3-mlx

pipenetwork/MiniMax-H3-MLX-8bit

Image-Text-to-Video • 9B • Updated 4 days ago • 630 • 5
pipenetwork/MiniMax-H3-MLX-6bit

Image-Text-to-Video • 8B • Updated 4 days ago • 309 • 2
pipenetwork/MiniMax-H3-MLX-4bit

Image-Text-to-Video • 7B • Updated 4 days ago • 509 • 1
pipenetwork/MiniMax-H3-MLX-bf16

Image-Text-to-Video • 33B • Updated 4 days ago • 373 • 3

Inkling-Small · MLX

276B-A12B multimodal MoE on Apple Silicon. Same code path as Inkling 975B. REAP-25 is free: github.com/PipeNetwork/inkling-mlx

pipenetwork/Inkling-Small-MLX-8bit

Image-Text-to-Text • 74B • Updated 8 days ago • 150
pipenetwork/Inkling-Small-MLX-6bit

Image-Text-to-Text • 58B • Updated 8 days ago • 134
pipenetwork/Inkling-Small-MLX-4bit

Image-Text-to-Text • 41B • Updated 8 days ago • 345 • 1
pipenetwork/Inkling-Small-MLX-REAP25-4bit

Image-Text-to-Text • 31B • Updated 8 days ago • 286 • 1

Inkling · MLX

975B-A41B multimodal MoE on Apple Silicon. Text+image+audio. Ported from scratch: github.com/PipeNetwork/inkling-mlx

pipenetwork/Inkling-MLX-8bit

Image-Text-to-Text • 266B • Updated 22 days ago • 716
pipenetwork/Inkling-MLX-6bit

Image-Text-to-Text • 207B • Updated 22 days ago • 844 • 1
pipenetwork/Inkling-MLX-4bit

Image-Text-to-Text • 148B • Updated 22 days ago • 1.11k • 1
pipenetwork/Inkling-MLX-REAP12-4bit

Image-Text-to-Text • 131B • Updated 22 days ago • 464

DeepSeek-V4-Flash · MLX

304B MoE on Apple Silicon. deepseek_v4 is in no released runtime — ported from scratch. Take mixed-4_8bit. github.com/PipeNetwork/deepseek-v4-mlx

pipenetwork/DeepSeek-V4-Flash-MLX-8bit

Text Generation • 81B • Updated 7 days ago • 440
pipenetwork/DeepSeek-V4-Flash-MLX-6bit

Text Generation • 64B • Updated 7 days ago • 297
pipenetwork/DeepSeek-V4-Flash-MLX-mixed-4_8bit

Text Generation • 47B • Updated 7 days ago • 558 • 1
pipenetwork/DeepSeek-V4-Flash-MLX-4bit

Text Generation • 46B • Updated 7 days ago • 472

Nemotron TwoTower · MLX

NVIDIA Nemotron TwoTower 30B-A3B diffusion LM in MLX for Apple Silicon: AR tower + two-tower diffusion, 4/6/8-bit + bf16.

pipenetwork/Nemotron-3-Nano-30B-A3B-context-mlx-4bit

Text Generation • 32B • Updated Jul 2 • 73
pipenetwork/Nemotron-3-Nano-30B-A3B-context-mlx-6bit

Text Generation • 32B • Updated Jul 2 • 100 • 1
pipenetwork/Nemotron-3-Nano-30B-A3B-context-mlx-8bit

Text Generation • 32B • Updated Jul 2 • 67
pipenetwork/Nemotron-3-Nano-30B-A3B-context-mlx-bf16

Text Generation • 32B • Updated Jul 2 • 123

Qwen3.6-35B-A3B — MLX

MLX (Apple Silicon) conversion of Qwen/Qwen3.6-35B-A3B in NVFP4 — the MLX analog of nvidia/Qwen3.6-35B-A3B-NVFP4. Text-only.

pipenetwork/Qwen3.6-35B-A3B-mlx-nvfp4

Text Generation • 35B • Updated Jun 26 • 75

Ornith-1.0-397B — MLX

MLX (Apple Silicon) conversions of deepreinforce-ai/Ornith-1.0-397B (Qwen3.5-MoE, text-only). 4/6/8-bit and bf16.

pipenetwork/Ornith-1.0-397B-mlx-4bit

Text Generation • 396B • Updated Jun 26 • 714 • 3
pipenetwork/Ornith-1.0-397B-mlx-6bit

Text Generation • 396B • Updated Jun 26 • 180
pipenetwork/Ornith-1.0-397B-mlx-8bit

Text Generation • 396B • Updated Jun 26 • 399 • 3

GLM-5.2 REAP (expert-pruned)

REAP expert-pruned GLM-5.2 (smaller/faster). REAP-25 near-lossless (+2.3% PPL); REAP-37 +7.3%; REAP-50 smallest but +37.5%.

pipenetwork/GLM-5.2-REAP25-MLX-4bit

Text Generation • 562B • Updated Jun 18 • 847 • 2
pipenetwork/GLM-5.2-REAP37-MLX-4bit

Text Generation • 472B • Updated Jun 18 • 654 • 1
pipenetwork/GLM-5.2-REAP50-MLX-4bit

Text Generation • 381B • Updated Jun 18 • 1.23k • 4

GLM-5.2 MLX

First MLX builds of zai-org/GLM-5.2 (glm_moe_dsa MoE): 4/5/6/8-bit + a 512GB-friendly mixed.

pipenetwork/GLM-5.2-MLX-mixed-3_6bit

Text Generation • 743B • Updated Jun 17 • 6.04k • 6
pipenetwork/GLM-5.2-MLX-4bit

Text Generation • 743B • Updated Jun 17 • 1.44k • 3
pipenetwork/GLM-5.2-MLX-5bit

Text Generation • 743B • Updated Jun 17 • 462
pipenetwork/GLM-5.2-MLX-6bit

Text Generation • 743B • Updated Jun 17 • 495

VISTA MLX

First MLX (Apple Silicon) quantizations of inclusionAI VISTA-9B and VISTA-4B (qwen3_5).

pipenetwork/VISTA-9B-MLX-8bit

Text Generation • 9B • Updated Jun 16 • 4
pipenetwork/VISTA-9B-MLX-6bit

Text Generation • 9B • Updated Jun 16 • 5
pipenetwork/VISTA-9B-MLX-5bit

Text Generation • 9B • Updated Jun 16 • 4
pipenetwork/VISTA-9B-MLX-4bit

Text Generation • 1B • Updated Jun 16 • 4

Rio-3.1-Open-30B MLX

First MLX (Apple Silicon) quantizations of prefeitura-rio/Rio-3.1-Open-30B (Qwen3-MoE): 4/5/6/8-bit.

pipenetwork/Rio-3.1-Open-30B-MLX-8bit

Text Generation • 31B • Updated Jun 15 • 19
pipenetwork/Rio-3.1-Open-30B-MLX-6bit

Text Generation • 31B • Updated Jun 15 • 8
pipenetwork/Rio-3.1-Open-30B-MLX-5bit

Text Generation • 31B • Updated Jun 15 • 7
pipenetwork/Rio-3.1-Open-30B-MLX-4bit

Text Generation • 31B • Updated Jun 15 • 28

Gemma-4-26B-A4B-it MLX

MLX quantizations of google/gemma-4-26B-A4B-it (MoE): 5/6/8-bit (4-bit available from mlx-community). Text-only.

pipenetwork/Gemma-4-26B-A4B-it-MLX-8bit

Text Generation • 25B • Updated Jun 14 • 6
pipenetwork/Gemma-4-26B-A4B-it-MLX-6bit

Text Generation • 25B • Updated Jun 14 • 9
pipenetwork/Gemma-4-26B-A4B-it-MLX-5bit

Text Generation • 25B • Updated Jun 14 • 25

Gemma-4-31B-it MLX

MLX (Apple Silicon) quantizations of google/gemma-4-31B-it: 4/5/6/8-bit. Text-only.

pipenetwork/Gemma-4-31B-it-MLX-8bit

Text Generation • 31B • Updated Jun 13 • 20
pipenetwork/Gemma-4-31B-it-MLX-6bit

Text Generation • 31B • Updated Jun 13 • 12
pipenetwork/Gemma-4-31B-it-MLX-5bit

Text Generation • 31B • Updated Jun 13 • 7
pipenetwork/Gemma-4-31B-it-MLX-4bit

Text Generation • 31B • Updated Jun 13 • 18

Kimi-K2.7-Code MLX

MLX build of Kimi-K2.7-Code. Base is natively 4-bit (int4 experts + bf16 rest); this keeps experts at 4-bit and lifts non-expert layers to 6-bit.

pipenetwork/Kimi-K2.7-Code-MLX-4bit-hiprec

Text Generation • 1T • Updated Jun 13 • 1.34k • 1

MiniMax-M3 MLX

MLX (Apple Silicon) text-only conversions of MiniMax-M3 (427B MoE): 3-bit to 8-bit plus a mixed-precision build.

pipenetwork/MiniMax-M3-MLX-8bit

Text Generation • 426B • Updated Jun 13 • 384 • 1
pipenetwork/MiniMax-M3-MLX-6bit

Text Generation • 426B • Updated Jun 13 • 286
pipenetwork/MiniMax-M3-MLX-4bit

Text Generation • 426B • Updated Jun 13 • 306
pipenetwork/MiniMax-M3-MLX-mixed-3_6bit

Text Generation • 426B • Updated Jun 13 • 518 • 2

Holo-3.1 MLX (computer-use)

First working MLX builds of H Company's Holo-3.1 vision-language computer-use agents (Qwen3.5-VL). Vision-validated. Apache-2.0.

pipenetwork/Holo-3.1-4B-MLX-4bit

Image-Text-to-Text • 1.0B • Updated Jun 5 • 174 • 3
pipenetwork/Holo-3.1-4B-MLX-8bit

Image-Text-to-Text • 2B • Updated Jun 5 • 39 • 1
pipenetwork/Holo-3.1-9B-MLX-4bit

Image-Text-to-Text • 2B • Updated Jun 5 • 94
pipenetwork/Holo-3.1-9B-MLX-8bit

Image-Text-to-Text • 3B • Updated Jun 5 • 82 • 1

Frog (SWE/debugging) MLX

MLX quants of Microsoft's FrogBoss-32B & FrogMini-14B (Qwen3 debugging finetunes, SWE-bench ~45% pass@1) for Apple Silicon.

pipenetwork/FrogMini-14B-2510-MLX-4bit

Text Generation • 15B • Updated Jun 5 • 12
pipenetwork/FrogMini-14B-2510-MLX-8bit

Text Generation • 15B • Updated Jun 5 • 12
pipenetwork/FrogBoss-32B-2510-MLX-4bit

Text Generation • 33B • Updated Jun 5 • 9
pipenetwork/FrogBoss-32B-2510-MLX-8bit

Text Generation • 33B • Updated Jun 5 • 9

Nemotron-3 MLX (Apple Silicon)

MLX quants of NVIDIA Nemotron-3 for Apple Silicon: Ultra 550B (4/5/6/8-bit) and dense Nano-4B (4/8-bit), converted with mlx-lm.

pipenetwork/NVIDIA-Nemotron-3-Ultra-550B-A55B-MLX-4bit

Text Generation • 549B • Updated Jun 5 • 110
pipenetwork/NVIDIA-Nemotron-3-Ultra-550B-A55B-MLX-8bit

Text Generation • 549B • Updated Jun 5 • 83
pipenetwork/NVIDIA-Nemotron-3-Nano-4B-MLX-8bit

1B • Updated Jun 5 • 8
pipenetwork/NVIDIA-Nemotron-3-Nano-4B-MLX-4bit

0.6B • Updated Jun 5 • 6