Back to search results
Qwen3.8-9B · Q3_K_M
NVIDIA RTX 5070 Ti16GBvLLM v0.53L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.8-9B (Q3_K_M) on NVIDIA RTX 5070 Ti with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
98.53 tok/s
Decode
Decode speed
475.97 tok/s
Prefill
Prefill speed
0.61 s
TTFT
Time to first token
14.95 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- vLLM · IQ3_S Decode 103.59 · Prefill 387.95 ·
- vLLM · Q3_K_M (current)Decode 98.53 · Prefill 475.97 ·
- Ollama · IQ3_XS Decode 89.42 · Prefill 466.92 ·
- Ollama · Q2_K Decode 98.9 · Prefill 326.08 ·
Core figures
- Decode (avg)
- 98.53 tok/s
- Prefill (avg)
- 475.97 tok/s
- TTFT (avg)
- 0.61 s
- VRAM (avg)
- 14.95 GB
- MTP acceptance rate
- —
- TTFB
- 0.79 GB
- Power draw
- 233.9 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-9B
- Quantization
- Q3_K_M
- Framework
- vLLM
- Version
- v0.53
- Context length
- 4096 tokens
- Batch size
- 32
- GPU layers
- 999
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 5070 Ti
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 14.95 GB
- OS
- Ubuntu 22.04
- Driver
- 572.83
- CUDA
- 12.4
- Power draw
- 233.9 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.53 · Ubuntu 22.04 · CUDA 12.4 · 4096 ctx
98.53 tok/s
Decode
475.97 tok/s
Prefill
0.61 s
TTFT
14.95 GB
VRAM
—
MTP
233.9 W
Power draw
L2 batch seed 2026-10-18: vLLM on hw_id=17 running model_id=52 at Q3_K_M