Qwen3.8-Flash-Next · IQ1_S
This page aggregates 1 real-world runs of Qwen3.8-Flash-Next (IQ1_S) on NVIDIA RTX 3060 12GB with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
70 tok/s
Decode
Decode speed
1,850 tok/s
Prefill
Prefill speed
1.5 s
TTFT
Time to first token
6.5 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- Strata · IQ1_S (current)Decode 70 · Prefill 1850 ·
Core figures
- Decode (avg)
- 70 tok/s
- Prefill (avg)
- 1,850 tok/s
- TTFT (avg)
- 1.5 s
- VRAM (avg)
- 6.5 GB
- MTP acceptance rate
- —
- TTFB
- — GB
- Power draw
- 170 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-Flash-Next
- Quantization
- IQ1_S
- Framework
- Strata
- Version
- 0.5.2
- Context length
- 4096 tokens
- Batch size
- 1
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 3060 12GB
- Nominal VRAM
- 12 GB
- Measured VRAM (avg)
- 6.5 GB
- OS
- Ubuntu 24.04.4 LTS
- Power draw
- 170 W
Get started
Original model resources
Base model resources may not match this quantization. Use the verified deployment weights above when available.
Sources & evidence
1 measured records in total, each traceable to its original source
0.5.2 · Ubuntu 24.04.4 LTS · 4096 ctx
70 tok/s
Decode
1,850 tok/s
Prefill
1.5 s
TTFT
6.5 GB
VRAM
—
MTP
170 W
Power draw
RTX 3060 12GB + Strata 0.5.2 + IQ1_S：short decode ~70 tok/s，128K ctx ~55 tok/s，prompt ~1850 tok/s，TTFT 1.5s。依赖 Strata 分层内存 + MTP 推测解码，IQ1_S 极致量化权重约 25GB 由 64GB DDR5 承载。