Back to search results
Qwen3.8-9B · IQ3_XS
NVIDIA RTX 309024GBStrata v0.22L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.8-9B (IQ3_XS) on NVIDIA RTX 3090 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
134.6 tok/s
Decode
Decode speed
685.06 tok/s
Prefill
Prefill speed
1.83 s
TTFT
Time to first token
13.82 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
17 days ago
Last verified
Performance
- llama.cpp · IQ2_XS Decode 104.18 · Prefill 429.42 ·
- llama.cpp · Q8_0 Decode 44.9 · Prefill 150.43 ·
- Strata · IQ3_XS (current)Decode 134.6 · Prefill 685.06 ·
- Strata · Q3_K_L Decode 103.74 · Prefill 393.26 ·
- llama.cpp · Q3_K_L Decode 79.17 · Prefill 416.87 ·
- Ollama · Q5_K_S Decode 58.86 · Prefill 223.43 ·
- Ollama · Q8_0 Decode 46.15 · Prefill 154.63 ·
- llama.cpp · Q3_K_S Decode 130.89 · Prefill 575.17 ·
- Ollama · IQ4_XS Decode 98.13 · Prefill 496.33 ·
Core figures
- Decode (avg)
- 134.6 tok/s
- Prefill (avg)
- 685.06 tok/s
- TTFT (avg)
- 1.83 s
- VRAM (avg)
- 13.82 GB
- MTP acceptance rate
- 0.7
- TTFB
- 1.08 GB
- Power draw
- 250.9 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-9B
- Quantization
- IQ3_XS
- Framework
- Strata
- Version
- v0.22
- Context length
- 4096 tokens
- Batch size
- 512
- 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
- NVIDIA RTX 3090
- Nominal VRAM
- 24 GB
- Measured VRAM (avg)
- 13.82 GB
- OS
- Windows 11 23H2
- Driver
- 565.57
- CUDA
- 12.6
- Power draw
- 250.9 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.22 · Windows 11 23H2 · CUDA 12.6 · 4096 ctx
134.6 tok/s
Decode
685.06 tok/s
Prefill
1.83 s
TTFT
13.82 GB
VRAM
0.7
MTP
250.9 W
Power draw
L2 batch seed 2026-10-19: Strata on hw_id=2 running model_id=52 at IQ3_XS