Back to search results
Qwen3.8-9B · IQ3_S
2x AMD Strix HaloStrata v0.35L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.8-9B (IQ3_S) on 2x AMD Strix Halo with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
220.16 tok/s
Decode
Decode speed
1,160.56 tok/s
Prefill
Prefill speed
0.86 s
TTFT
Time to first token
14.57 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- llama.cpp · IQ1_S Decode 185.41 · Prefill 664.26 ·
- llama.cpp · IQ4_XS Decode 145.51 · Prefill 650.25 ·
- Strata · IQ2_M Decode 243.64 · Prefill 1152.92 ·
- Strata · IQ3_S (current)Decode 220.16 · Prefill 1160.56 ·
Core figures
- Decode (avg)
- 220.16 tok/s
- Prefill (avg)
- 1,160.56 tok/s
- TTFT (avg)
- 0.86 s
- VRAM (avg)
- 14.57 GB
- MTP acceptance rate
- 0.65
- TTFB
- 1.76 GB
- Power draw
- 59.2 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-9B
- Quantization
- IQ3_S
- Framework
- Strata
- Version
- v0.35
- Context length
- 32768 tokens
- Batch size
- 256
- GPU layers
- 8
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- 2x AMD Strix Halo
- Measured VRAM (avg)
- 14.57 GB
- OS
- macOS 15.0
- Driver
- 570.86
- CUDA
- N/A
- Power draw
- 59.2 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.35 · macOS 15.0 · CUDA N/A · 32768 ctx
220.16 tok/s
Decode
1,160.56 tok/s
Prefill
0.86 s
TTFT
14.57 GB
VRAM
0.65
MTP
59.2 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=88 running model_id=52 at IQ3_S