DreamFoundries/Qwen3.6-35B-A3B-4bit
Text Generation • 35B • Updated • 55
Qwen 3.6 MLX Quantizations
MLX-LM affine quantizations for Qwen3.6; see each model card for details.
Note 4-bit MLX-LM affine quantization of Qwen/Qwen3.6-35B-A3B. No comparative benchmarks yet.
DreamFoundries/Qwen3.6-35B-A3B-6bit
Text Generation • 35B • Updated • 151Note 6-bit MLX-LM affine quantization of Qwen/Qwen3.6-35B-A3B. No comparative benchmarks yet.
DreamFoundries/Qwen3.6-35B-A3B-8bit
Text Generation • 35B • Updated • 188Note 8-bit MLX-LM affine quantization of Qwen/Qwen3.6-35B-A3B. No comparative benchmarks yet.
DreamFoundries/Qwen3.6-27B-4bit
Text Generation • 27B • Updated • 180Note 4-bit MLX-LM affine quantization of Qwen/Qwen3.6-27B. No comparative benchmarks yet.
DreamFoundries/Qwen3.6-27B-6bit
Text Generation • 27B • Updated • 170Note 6-bit MLX-LM affine quantization of Qwen/Qwen3.6-27B. No comparative benchmarks yet.
DreamFoundries/Qwen3.6-27B-8bit
Text Generation • 27B • Updated • 275Note 8-bit MLX-LM affine quantization of Qwen/Qwen3.6-27B. No comparative benchmarks yet.