Tenzro
Language

Muse Glimmer 30B DFlash Drafter

DFlash block-diffusion speculative drafter for Muse-Glimmer-30B. Pair via `--spec-type draft-dflash` for ~2x decode.
Apache 2.0Source verified
Specification
Model ID
muse-glimmer-30b-dflash
Family
muse-glimmer
Modality
Language
Parameters
DFlash drafter
Context
131,072 tokens
Quantization
Q4_K
Weights
1.9 GB
Minimum RAM
4 GB
Source

Weights and provenance.

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 muse-glimmer-30b-dflash

# Serve it
tenzro model serve muse-glimmer-30b-dflash

# 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":"muse-glimmer-30b-dflash"}]}'
Same family
← All models