Language

Qwen 3.6 35B-A3B MTP (MoE)

Qwen 3.6 35B-A3B MoE with built-in Multi-Token-Prediction head. Single-file MTP GGUF — no separate drafter needed. Unsloth: 240 t/s on RTX 6000.

Apache 2.0Source verified

Specification

Model ID

qwen3.6-35b-a3b-mtp

Family

qwen3.6

Modality

Language

Parameters

35B (MoE, 3B active)

Context

262,144 tokens

Quantization

UD-Q4_K_XL

Weights

20.5 GB

Minimum RAM

28 GB

Source

Weights and provenance.

Repository

unsloth/Qwen3.6-35B-A3B-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 qwen3.6-35b-a3b-mtp

# Serve it
tenzro model serve qwen3.6-35b-a3b-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":"qwen3.6-35b-a3b-mtp"}]}'

Same family

Qwen 3.6 27B

27B

Qwen 3.6 27B Fable-Fusion (MTP, uncensored)

27B

Qwen 3.6 27B (MTP)

27B

Qwen 3.6 35B-A3B (MoE)

35B (MoE, 3B active)

← All models