Back to search results
Qwen3.5-0.8B · Q3_K_S
NVIDIA RTX 309024GBvLLM v0.30L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-0.8B (Q3_K_S) on NVIDIA RTX 3090 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
241.45 tok/s
Decode
Decode speed
1,059.79 tok/s
Prefill
Prefill speed
1.15 s
TTFT
Time to first token
3.19 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- vLLM · Q3_K_M Decode 217.39 · Prefill 922.41 ·
- vLLM · Q3_K_S (current)Decode 241.45 · Prefill 1059.79 ·
- Ollama · Q3_K_L Decode 178.6 · Prefill 868.06 ·
- Ollama · Q5_K_M Decode 146.73 · Prefill 547.3 ·
- llama.cpp · IQ2_M Decode 352.68 · Prefill 1697.91 ·
- llama.cpp · Q3_K_L Decode 315.76 · Prefill 1365.7 ·
- Strata · IQ4_XS Decode 382.98 · Prefill 1282.3 ·
- Strata · Q3_K_M Decode 336.19 · Prefill 1574.41 ·
Core figures
- Decode (avg)
- 241.45 tok/s
- Prefill (avg)
- 1,059.79 tok/s
- TTFT (avg)
- 1.15 s
- VRAM (avg)
- 3.19 GB
- MTP acceptance rate
- —
- TTFB
- 1.93 GB
- Power draw
- 260.2 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-0.8B
- Quantization
- Q3_K_S
- Framework
- vLLM
- Version
- v0.30
- Context length
- 32768 tokens
- Batch size
- 16
- GPU layers
- 999
- Flash Attention
- Off
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)
- 3.19 GB
- OS
- Windows 11 24H2
- Driver
- 572.83
- CUDA
- 12.6
- Power draw
- 260.2 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.30 · Windows 11 24H2 · CUDA 12.6 · 32768 ctx
241.45 tok/s
Decode
1,059.79 tok/s
Prefill
1.15 s
TTFT
3.19 GB
VRAM
—
MTP
260.2 W
Power draw
L2 batch seed 2026-10-18: vLLM on hw_id=2 running model_id=51 at Q3_K_S