Python · Apache-2.0
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).
★ 134
Stars
16 forks · 9 open issues
+4.0/wk
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
23.2
Momentum / 100
see the breakdown below
2mo ago
Created
last push 23d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 3.8 | +4.0/wk, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | last week ran 0.71× the monthly pace |
| Freshness | 15 | 13.3 | last push 23d ago; decays to zero at 180 days |
| Scale | 15 | 6.2 | 134 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 23.2 | sum of the above |
Detail
| Topics | 256k-contextcpu-offloadingdual-gpufp8int4llm-inferencelocal-llmmoemtpmulti-gpuquantizationqwenqwen3-8qwen3-8-flash-nextqwen38rtx-3090rtx3090rtx4090speculative-decodingvllm |
| Matched on | LLM & Inference (llm-inference) |
| Short window | +4 stars over 7 days = 0.6/day |
| Long window | +21 stars over 26 days = 0.8/day |
| Lifetime average | 2.01 stars/day over 67 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |