Qwen3.8-27B · IQ2_M
This page aggregates 1 real-world runs of Qwen3.8-27B (IQ2_M) on NVIDIA H100 80GB HBM3 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
325.92 tok/s
Decode
Decode speed
1,772.8 tok/s
Prefill
Prefill speed
0.35 s
TTFT
Time to first token
31.58 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
17 days ago
Last verified
Performance
- vLLM · Q4_K_M Decode 224.13 · Prefill 1208.86 ·
- vLLM · Q5_K_M Decode 206.52 · Prefill 1029.93 ·
- Strata · IQ2_M (current)Decode 325.92 · Prefill 1772.8 ·
Core figures
- Decode (avg)
- 325.92 tok/s
- Prefill (avg)
- 1,772.8 tok/s
- TTFT (avg)
- 0.35 s
- VRAM (avg)
- 31.58 GB
- MTP acceptance rate
- 0.64
- TTFB
- 2.61 GB
- Power draw
- 643.5 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-27B
- Quantization
- IQ2_M
- Framework
- Strata
- Version
- v0.49
- Context length
- 8192 tokens
- Batch size
- 256
- GPU layers
- 5
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA H100 80GB HBM3
- Nominal VRAM
- 80 GB
- Measured VRAM (avg)
- 31.58 GB
- OS
- Ubuntu 24.04
- Driver
- 570.86
- CUDA
- 12.8
- Power draw
- 643.5 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
v0.49 · Ubuntu 24.04 · CUDA 12.8 · 8192 ctx
325.92 tok/s
Decode
1,772.8 tok/s
Prefill
0.35 s
TTFT
31.58 GB
VRAM
0.64
MTP
643.5 W
Power draw
L2 batch seed 2026-10-19: Strata on hw_id=55 running model_id=5 at IQ2_M