← Back to Models

qwen3.5-35b-a3b

qwen/qwen3.5-35b-a3b

View on HuggingFace
Publisher
qwen
Architecture
qwen35moe(sparse)
Parameters
35B
Quantization
Q4_K_M (4.0 bpw)
Format
gguf
Max Context
262k tokens
Type
llm
File Size
20.56 GB
Est. RAM
22.1 GB
Est. VRAM
22.1 GB(~3B active)
Capabilities
visiontrained_for_tool_usereasoning

Benchmark Results

Compare Models