Qwen3.8-27B · Q2_K
This page aggregates 1 real-world runs of Qwen3.8-27B (Q2_K) on NVIDIA H20 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
52.83 tok/s
Decode
Decode speed
205.52 tok/s
Prefill
Prefill speed
0.9 s
TTFT
Time to first token
33.29 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
17 days ago
Last verified
Performance
- llama.cpp · IQ2_XS Decode 42.1 · Prefill 229.32 ·
- Strata · Q2_K (current)Decode 52.83 · Prefill 205.52 ·
- Strata · Q4_K_M Decode 39.14 · Prefill 148.55 ·
Core figures
- Decode (avg)
- 52.83 tok/s
- Prefill (avg)
- 205.52 tok/s
- TTFT (avg)
- 0.9 s
- VRAM (avg)
- 33.29 GB
- MTP acceptance rate
- 0.61
- TTFB
- 0.42 GB
- Power draw
- 306.9 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-27B
- Quantization
- Q2_K
- Framework
- Strata
- Version
- v0.36
- Context length
- 8192 tokens
- Batch size
- 1024
- GPU layers
- 8
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA H20
- Nominal VRAM
- 97 GB
- Measured VRAM (avg)
- 33.29 GB
- OS
- Windows 11 24H2
- Driver
- 570.86
- CUDA
- 12.4
- Power draw
- 306.9 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
v0.36 · Windows 11 24H2 · CUDA 12.4 · 8192 ctx
52.83 tok/s
Decode
205.52 tok/s
Prefill
0.9 s
TTFT
33.29 GB
VRAM
0.61
MTP
306.9 W
Power draw
L2 batch seed 2026-10-19: Strata on hw_id=56 running model_id=5 at Q2_K