Language
Qwen 3.8 27B (3-bit)
Qwen 3.8 27B dense at 3-bit, sized to fit a 16 GB consumer GPU. Measured 62.0 tok/s on an RTX 5070 Ti against 19.6 tok/s for the 4-bit build on a GB10 — decode is bandwidth-bound, and this build reads 13.44 GB per token.
Apache 2.0Source verified
Specification
Model ID
qwen3.8-27b-q3Family
qwen3.8
Modality
Language
Parameters
27B (dense)
Context
262,144 tokens
Quantization
UD-Q3_K_XL
Weights
12.5 GB
Minimum RAM
18 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 qwen3.8-27b-q3
# Serve it
tenzro model serve qwen3.8-27b-q3
# 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":"qwen3.8-27b-q3"}]}'Same family