← Back to Models

qwen3.5-122b-a10b

qwen3.5-122b-a10b

Loaded
Publisher
unsloth
Architecture
qwen35moe(sparse)
Parameters
122B
Quantization
Q2_K_XL (2.0 bpw)
Format
gguf
Max Context
262k tokens
Type
llm
File Size
40.65 GB
Est. RAM
42.2 GB
Est. VRAM
42.2 GB(~10B active)
Capabilities
visiontrained_for_tool_use

Benchmark Results

Compare Models