PrototypeCommon
DominikBucko/qwen38-flash-next-2x3090
Qwen3.8-Flash-Next on 2× RTX 3090: with 128 GB RAM up to 4,191 tok/s prefill · 111.5 tok/s decode (131K prompt), full 256K window at 2,865 tok/s; with 64 GB RAM 3,410 tok/s prefill · 84 tok/s decode. New: opt-in uncensored mode (runtime abliteration, no new weights).
- Owner
- DominikBucko (personal account)
- Stars
- Stars: 132
- Forks
- Forks: 16
- Language
- Python
- License
- Apache-2.0
- Created
- 2026
- Topics
- llm-inferencequantizationqwenrtx3090speculative-decodingvllmcpu-offloadingdual-gpufp8int4
- Tier
- Prototype (100 to 249 ★) What this tier means
Nearby in Python
All Python repos- SimpleJev/JevAnyStars: 132PythonPrototype
- proffitteoy/Mathematician-HumanizerStars: 132PythonPrototype
- sanjayadanushka712/Ghost-NightStars: 132PythonPrototype
- jacobian/jellyrollStars: 132PythonPrototype
- moraes/tipfyStars: 132PythonPrototype
- zacharyvoase/cssminStars: 132PythonPrototype