Language
Qwen3.8-Flash-Next MTP Drafter
Qwen's jointly-trained Multi-Token Prediction head for Qwen3.8-Flash-Next, exported as a standalone GGUF sidecar (Unsloth's main build strips it). Pair with the Flash-Next target via `--spec-type draft-mtp`.
Apache 2.0Source verified
Specification
Model ID
qwen3.8-flash-next-mtp-draftFamily
qwen3.8-flash-next
Modality
Language
Parameters
MTP head
Context
262,144 tokens
Quantization
Q8_0
Weights
3.9 GB
Minimum RAM
6 GB
Source
Weights and provenance.
Repository
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 qwen3.8-flash-next-mtp-draft
# Serve it
tenzro model serve qwen3.8-flash-next-mtp-draft
# 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":"qwen3.8-flash-next-mtp-draft"}]}'Same family