Language

Qwen 3.5 397B-A17B (MoE) (MTP)

Qwen 3.5 397B-A17B (MoE) with built-in Multi-Token-Prediction head. Single-file MTP GGUF — no separate drafter needed. Unsloth measures ~1.5-2× speedup over the non-MTP baseline.

Apache 2.0Source verified

Specification

Model ID

qwen3.5-397b-a17b-mtp

Family

qwen3.5

Modality

Language

Parameters

397B (MoE, 17B active)

Context

131,072 tokens

Quantization

UD-Q4_K_XL

Weights

223.5 GB

Minimum RAM

256 GB

Source

Weights and provenance.

Repository

unsloth/Qwen3.5-397B-A17B-MTP-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-mtp

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

# 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-mtp"}]}'