First MLX builds of zai-org/GLM-5.2 (glm_moe_dsa MoE): 4/5/6/8-bit + a 512GB-friendly mixed.
Open to Collab
Pipenetwork
pipenetwork
AI & ML interests
AI & ML
Recent Activity
published a model about 2 hours ago
pipenetwork/GLM-5.2-MLX-6bit updated a collection about 2 hours ago
GLM-5.2 MLX updated a model about 2 hours ago
pipenetwork/GLM-5.2-MLX-5bitOrganizations
None yet
First MLX (Apple Silicon) quantizations of prefeitura-rio/Rio-3.1-Open-30B (Qwen3-MoE): 4/5/6/8-bit.
MLX quantizations of google/gemma-4-26B-A4B-it (MoE): 5/6/8-bit (4-bit available from mlx-community). Text-only.
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.
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 • 205 • 2 -
pipenetwork/Holo-3.1-4B-MLX-8bit
Image-Text-to-Text • 2B • Updated • 107 • 1 -
pipenetwork/Holo-3.1-9B-MLX-4bit
Image-Text-to-Text • 2B • Updated • 198 -
pipenetwork/Holo-3.1-9B-MLX-8bit
Image-Text-to-Text • 3B • Updated • 213 • 1
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 • 204 -
pipenetwork/NVIDIA-Nemotron-3-Ultra-550B-A55B-MLX-5bit
Text Generation • 549B • Updated • 159 -
pipenetwork/NVIDIA-Nemotron-3-Ultra-550B-A55B-MLX-6bit
Text Generation • 549B • Updated • 166 -
pipenetwork/NVIDIA-Nemotron-3-Ultra-550B-A55B-MLX-8bit
Text Generation • 549B • Updated • 251
First MLX (Apple Silicon) quantizations of inclusionAI VISTA-9B and VISTA-4B (qwen3_5).
First MLX builds of Macaron-V1-Preview-749B (glm_moe_dsa, 749B MoE): a tight 4-bit and a 512GB-friendly mixed.
MLX (Apple Silicon) quantizations of google/gemma-4-31B-it: 4/5/6/8-bit. Text-only.
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 • 1.27k • 1 -
pipenetwork/MiniMax-M3-MLX-6bit
Text Generation • 426B • Updated • 885 -
pipenetwork/MiniMax-M3-MLX-4bit
Text Generation • 426B • Updated • 802 -
pipenetwork/MiniMax-M3-MLX-mixed-3_6bit
Text Generation • 426B • Updated • 985 • 1
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 • 16 -
pipenetwork/FrogMini-14B-2510-MLX-8bit
Text Generation • 15B • Updated • 21 -
pipenetwork/FrogBoss-32B-2510-MLX-4bit
Text Generation • 33B • Updated • 18 -
pipenetwork/FrogBoss-32B-2510-MLX-8bit
Text Generation • 33B • Updated • 14
First MLX builds of zai-org/GLM-5.2 (glm_moe_dsa MoE): 4/5/6/8-bit + a 512GB-friendly mixed.
First MLX (Apple Silicon) quantizations of inclusionAI VISTA-9B and VISTA-4B (qwen3_5).
First MLX (Apple Silicon) quantizations of prefeitura-rio/Rio-3.1-Open-30B (Qwen3-MoE): 4/5/6/8-bit.
First MLX builds of Macaron-V1-Preview-749B (glm_moe_dsa, 749B MoE): a tight 4-bit and a 512GB-friendly mixed.
MLX quantizations of google/gemma-4-26B-A4B-it (MoE): 5/6/8-bit (4-bit available from mlx-community). Text-only.
MLX (Apple Silicon) quantizations of google/gemma-4-31B-it: 4/5/6/8-bit. Text-only.
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.
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 • 1.27k • 1 -
pipenetwork/MiniMax-M3-MLX-6bit
Text Generation • 426B • Updated • 885 -
pipenetwork/MiniMax-M3-MLX-4bit
Text Generation • 426B • Updated • 802 -
pipenetwork/MiniMax-M3-MLX-mixed-3_6bit
Text Generation • 426B • Updated • 985 • 1
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 • 205 • 2 -
pipenetwork/Holo-3.1-4B-MLX-8bit
Image-Text-to-Text • 2B • Updated • 107 • 1 -
pipenetwork/Holo-3.1-9B-MLX-4bit
Image-Text-to-Text • 2B • Updated • 198 -
pipenetwork/Holo-3.1-9B-MLX-8bit
Image-Text-to-Text • 3B • Updated • 213 • 1
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 • 16 -
pipenetwork/FrogMini-14B-2510-MLX-8bit
Text Generation • 15B • Updated • 21 -
pipenetwork/FrogBoss-32B-2510-MLX-4bit
Text Generation • 33B • Updated • 18 -
pipenetwork/FrogBoss-32B-2510-MLX-8bit
Text Generation • 33B • Updated • 14
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 • 204 -
pipenetwork/NVIDIA-Nemotron-3-Ultra-550B-A55B-MLX-5bit
Text Generation • 549B • Updated • 159 -
pipenetwork/NVIDIA-Nemotron-3-Ultra-550B-A55B-MLX-6bit
Text Generation • 549B • Updated • 166 -
pipenetwork/NVIDIA-Nemotron-3-Ultra-550B-A55B-MLX-8bit
Text Generation • 549B • Updated • 251