← Back to Models

qwen3.5-122b-a10b

mlx-community/qwen3.5-122b-a10b

View on HuggingFace
Publisher
mlx-community
Architecture
qwen3_5_moe(sparse)
Parameters
122B
Quantization
4bit (4.0 bpw)
Format
mlx
Max Context
262k tokens
Type
llm
File Size
64.84 GB
Est. RAM
66.3 GB
Est. VRAM
66.3 GB(~10B active)
Capabilities
visiontrained_for_tool_use

Benchmark Results

Compare Models