Something went wrong. Try again.
The fastest decode and prefill for 4-bit Qwen3.8-27B on one RTX 3090 that preserves the model's intelligence
Something went wrong. Try again.
- Languages
- 5
- Total size
- 1.5 MB
- Primary language
- Python
Python: 93%, 1.4 MB
Shell: 5%, 70 kB
Docker: 1%, 18 kB
Nix: <1%, 9.8 kB
C: <1%, 8.5 kB
| Language | Size | Share |
|---|---|---|
| Python | 1.4 MB | 93% |
| Shell | 70 kB | 5% |
| Docker | 18 kB | 1% |
| Nix | 9.8 kB | <1% |
| C | 8.5 kB | <1% |