Back to search results
Qwen3.5-0.8B · Q3_K_S
NVIDIA RTX 4060 Ti 16GB16GBvLLM v0.44L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-0.8B (Q3_K_S) on NVIDIA RTX 4060 Ti 16GB with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
239.77 tok/s
Decode
Decode speed
1,073.87 tok/s
Prefill
Prefill speed
1.18 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
5 days ago
Last verified
Performance
- vLLM · FP16 Decode 128.16 · Prefill 630.91 ·
- vLLM · Q4_K_S Decode 240.41 · Prefill 996.87 ·
- Ollama · Q5_K_S Decode 177.61 · Prefill 661.12 ·
- Ollama · Q6_K Decode 170.01 · Prefill 704.45 ·
- vLLM · IQ4_XS Decode 206.77 · Prefill 955.7 ·
- vLLM · Q3_K_S (current)Decode 239.77 · Prefill 1073.87 ·
- Ollama · IQ1_S Decode 259.18 · Prefill 1280.06 ·
Core figures
- Decode (avg)
- 239.77 tok/s
- Prefill (avg)
- 1,073.87 tok/s
- TTFT (avg)
- 1.18 s
- VRAM (avg)
- 3.19 GB
- MTP acceptance rate
- —
- TTFB
- 1.92 GB
- Power draw
- 344.6 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-0.8B
- Quantization
- Q3_K_S
- Framework
- vLLM
- Version
- v0.44
- Context length
- 4096 tokens
- Batch size
- 32
- 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 4060 Ti 16GB
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 3.19 GB
- OS
- Ubuntu 22.04
- Driver
- 560.94
- CUDA
- 12.8
- Power draw
- 344.6 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.44 · Ubuntu 22.04 · CUDA 12.8 · 4096 ctx
239.77 tok/s
Decode
1,073.87 tok/s
Prefill
1.18 s
TTFT
3.19 GB
VRAM
—
MTP
344.6 W
Power draw
L2 batch seed 2026-10-13: vLLM on hw_id=3 running model_id=51 at Q3_K_S