MLX affine 4-bit, 6-bit, and 8-bit quantizations of Qwen/Qwen3.8-27B.
🏗️ Building on HF
DreamFoundries
DreamFoundries
AI & ML interests
None yet
Recent Activity
updated a collection 11 days ago
Qwen3.8 MLX Quants updated a collection 11 days ago
Qwen3.8 MLX Quants updated a collection 11 days ago
Qwen3.8 MLX QuantsOrganizations
None yet
MLX-LM affine quantizations for Qwen AgentWorld; see each model card for details.
MLX-LM affine quantizations for SuperQwen AgentWorld; see each model card for details.
MLX-LM affine quantizations for Ornith 1.0 models; see each model card for details.
MLX-LM affine quantizations for Qwen3.6; see each model card for details.
MLX-LM affine quantizations for Gemma4; see each model card for details.
MLX-LM Laguna S 2.1 quantizations. No comparative benchmarks are available yet.
MLX-LM affine quantizations for Agents A1; see each model card for details.
MLX-LM affine quantizations for SuperGemma4; see each model card for details.
-
DreamFoundries/SuperGemma-4-12b-abliterated-4bit
Text Generation • 12B • Updated • 103 -
DreamFoundries/SuperGemma-4-12b-abliterated-6bit
Text Generation • 12B • Updated • 47 -
DreamFoundries/SuperGemma-4-12b-abliterated-8bit
Text Generation • 12B • Updated • 49 -
DreamFoundries/supergemma4-e4b-abliterated-4bit
Text Generation • 1B • Updated • 160
MLX-LM affine quantizations for Nemotron 3; see each model card for details.
-
DreamFoundries/NVIDIA-Nemotron-3-Super-120B-A12B-BF16-4bit
Text Generation • 121B • Updated • 85 -
DreamFoundries/NVIDIA-Nemotron-3-Super-120B-A12B-BF16-6bit
Text Generation • 121B • Updated • 93 -
DreamFoundries/NVIDIA-Nemotron-3-Super-120B-A12B-BF16-8bit
Text Generation • 121B • Updated • 93 -
DreamFoundries/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16-4bit
Text Generation • 32B • Updated • 28
MLX-LM affine quantizations for Qwen3.5; see each model card for details.
MLX affine 4-bit, 6-bit, and 8-bit quantizations of Qwen/Qwen3.8-27B.
MLX-LM Laguna S 2.1 quantizations. No comparative benchmarks are available yet.
MLX-LM affine quantizations for Qwen AgentWorld; see each model card for details.
MLX-LM affine quantizations for Agents A1; see each model card for details.
MLX-LM affine quantizations for SuperQwen AgentWorld; see each model card for details.
MLX-LM affine quantizations for SuperGemma4; see each model card for details.
-
DreamFoundries/SuperGemma-4-12b-abliterated-4bit
Text Generation • 12B • Updated • 103 -
DreamFoundries/SuperGemma-4-12b-abliterated-6bit
Text Generation • 12B • Updated • 47 -
DreamFoundries/SuperGemma-4-12b-abliterated-8bit
Text Generation • 12B • Updated • 49 -
DreamFoundries/supergemma4-e4b-abliterated-4bit
Text Generation • 1B • Updated • 160
MLX-LM affine quantizations for Ornith 1.0 models; see each model card for details.
MLX-LM affine quantizations for Nemotron 3; see each model card for details.
-
DreamFoundries/NVIDIA-Nemotron-3-Super-120B-A12B-BF16-4bit
Text Generation • 121B • Updated • 85 -
DreamFoundries/NVIDIA-Nemotron-3-Super-120B-A12B-BF16-6bit
Text Generation • 121B • Updated • 93 -
DreamFoundries/NVIDIA-Nemotron-3-Super-120B-A12B-BF16-8bit
Text Generation • 121B • Updated • 93 -
DreamFoundries/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16-4bit
Text Generation • 32B • Updated • 28
MLX-LM affine quantizations for Qwen3.6; see each model card for details.
MLX-LM affine quantizations for Qwen3.5; see each model card for details.
MLX-LM affine quantizations for Gemma4; see each model card for details.