Tenzro
Language

Qwen 3.5 397B-A17B (MoE)

Qwen 3.5 frontier MoE — 397B total, 17B active per token. Multi-GPU replicas only; Unsloth ships an MTP variant in `unsloth/Qwen3.5-397B-A17B-MTP-GGUF` for compatible runtimes.
Apache 2.0Source verified
Specification
Model ID
qwen3.5-397b-a17b
Family
qwen3.5
Modality
Language
Parameters
397B (MoE, 17B active)
Context
262,144 tokens
Quantization
Q4_K_M
Weights
223.5 GB
Minimum RAM
256 GB
Source

Weights and provenance.

Repository
unsloth/Qwen3.5-397B-A17B-GGUF
Registry license
Apache 2.0
Source license
apache-2.0
Access
Open — weights fetch without accepting additional terms.
Serve it
# Pull the weights onto a node
tenzro model download qwen3.5-397b-a17b

# Serve it
tenzro model serve qwen3.5-397b-a17b

# Or query the registry entry over JSON-RPC
curl https://rpc.tenzro.xyz \
  -X POST -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,
       "method":"tenzro_getModel",
       "params":[{"model_id":"qwen3.5-397b-a17b"}]}'
Same family
Qwen 3.5 0.8B
0.8B
Qwen 3.5 0.8B (MTP)
0.8B
Qwen 3.5 122B-A10B (MoE)
122B (MoE, 10B active)
Qwen 3.5 122B-A10B (MoE) (MTP)
122B (MoE, 10B active)
Qwen 3.5 27B
27B
Qwen 3.5 27B (MTP)
27B
Qwen 3.5 2B
2B
Qwen 3.5 2B (MTP)
2B
Qwen 3.5 35B-A3B (MoE)
35B (MoE, 3B active)
Qwen 3.5 35B-A3B (MoE) (MTP)
35B (MoE, 3B active)
Qwen 3.5 397B-A17B (MoE) (MTP)
397B (MoE, 17B active)
Qwen 3.5 4B
4B
← All models