Qwen 3.5 MLX Quantizations

DreamFoundries 's Collections

Qwen3.8 MLX Quants

Laguna S 2.1 MLX Quantizations

Qwen AgentWorld MLX Quantizations

Agents A1 MLX Quantizations

SuperQwen AgentWorld MLX Quantizations

SuperGemma4 MLX Quantizations

Ornith 1.0 MLX Quantizations

Nemotron 3 MLX Quantizations

Qwen 3.6 MLX Quantizations

Qwen 3.5 MLX Quantizations

Gemma 4 MLX Quantizations

updated Jun 29

MLX-LM affine quantizations for Qwen3.5; see each model card for details.

Upvote

DreamFoundries/Qwen3.5-122B-A10B-4bit

Text Generation • 122B • Updated Jun 29 • 65

Note 4-bit MLX-LM affine quantization of Qwen/Qwen3.5-122B-A10B. No comparative benchmarks yet.
DreamFoundries/Qwen3.5-122B-A10B-6bit

Text Generation • 122B • Updated Jun 29 • 66

Note 6-bit MLX-LM affine quantization of Qwen/Qwen3.5-122B-A10B. No comparative benchmarks yet.
DreamFoundries/Qwen3.5-122B-A10B-8bit

Text Generation • 122B • Updated Jun 29 • 98

Note 8-bit MLX-LM affine quantization of Qwen/Qwen3.5-122B-A10B. No comparative benchmarks yet.
DreamFoundries/Qwen3.5-9B-4bit

Text Generation • 1B • Updated Jun 29 • 17

Note 4-bit MLX-LM affine quantization of Qwen/Qwen3.5-9B. No comparative benchmarks yet.
DreamFoundries/Qwen3.5-9B-6bit

Text Generation • 9B • Updated Jun 29 • 28

Note 6-bit MLX-LM affine quantization of Qwen/Qwen3.5-9B. No comparative benchmarks yet.
DreamFoundries/Qwen3.5-9B-8bit

Text Generation • 9B • Updated Jun 29 • 24

Note 8-bit MLX-LM affine quantization of Qwen/Qwen3.5-9B. No comparative benchmarks yet.
DreamFoundries/Qwen3.5-4B-4bit

Text Generation • 0.7B • Updated Jun 29 • 109

Note 4-bit MLX-LM affine quantization of Qwen/Qwen3.5-4B. No comparative benchmarks yet.
DreamFoundries/Qwen3.5-4B-6bit

Text Generation • 0.9B • Updated Jun 29 • 62

Note 6-bit MLX-LM affine quantization of Qwen/Qwen3.5-4B. No comparative benchmarks yet.
DreamFoundries/Qwen3.5-4B-8bit

Text Generation • 1B • Updated Jun 29 • 17

Note 8-bit MLX-LM affine quantization of Qwen/Qwen3.5-4B. No comparative benchmarks yet.
DreamFoundries/Qwen3.5-2B-4bit

Text Generation • 0.3B • Updated Jun 29 • 54

Note 4-bit MLX-LM affine quantization of Qwen/Qwen3.5-2B. No comparative benchmarks yet.
DreamFoundries/Qwen3.5-2B-6bit

Text Generation • 0.4B • Updated Jun 29 • 19

Note 6-bit MLX-LM affine quantization of Qwen/Qwen3.5-2B. No comparative benchmarks yet.
DreamFoundries/Qwen3.5-2B-8bit

Text Generation • 0.5B • Updated Jun 29 • 21

Note 8-bit MLX-LM affine quantization of Qwen/Qwen3.5-2B. No comparative benchmarks yet.
DreamFoundries/Qwen3.5-0.8B-4bit

Text Generation • 0.1B • Updated Jun 29 • 203

Note 4-bit MLX-LM affine quantization of Qwen/Qwen3.5-0.8B. No comparative benchmarks yet.
DreamFoundries/Qwen3.5-0.8B-6bit

Text Generation • 0.2B • Updated Jun 29 • 12

Note 6-bit MLX-LM affine quantization of Qwen/Qwen3.5-0.8B. No comparative benchmarks yet.
DreamFoundries/Qwen3.5-0.8B-8bit

Text Generation • 0.2B • Updated Jun 29 • 27

Note 8-bit MLX-LM affine quantization of Qwen/Qwen3.5-0.8B. No comparative benchmarks yet.

Upvote