Back to search results
Qwen3.5-0.8B · Q4_K_S
NVIDIA RTX 4080 Super16GBvLLM v0.47L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-0.8B (Q4_K_S) on NVIDIA RTX 4080 Super with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
370.71 tok/s
Decode
Decode speed
1,429.25 tok/s
Prefill
Prefill speed
0.63 s
TTFT
Time to first token
3.41 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
17 days ago
Last verified
Performance
- vLLM · Q3_K_S Decode 302.38 · Prefill 993.94 ·
- vLLM · Q4_K_S (current)Decode 370.71 · Prefill 1429.25 ·
- Ollama · IQ3_S Decode 352.12 · Prefill 1849.99 ·
- Ollama · IQ3_XS Decode 393.56 · Prefill 2131.15 ·
- llama.cpp · Q4_K_M Decode 344.73 · Prefill 1737.55 ·
- vLLM · IQ1_S Decode 314.79 · Prefill 1409.84 ·
Core figures
- Decode (avg)
- 370.71 tok/s
- Prefill (avg)
- 1,429.25 tok/s
- TTFT (avg)
- 0.63 s
- VRAM (avg)
- 3.41 GB
- MTP acceptance rate
- —
- TTFB
- 2.97 GB
- Power draw
- 223.8 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-0.8B
- Quantization
- Q4_K_S
- Framework
- vLLM
- Version
- v0.47
- Context length
- 16384 tokens
- Batch size
- 8
- 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 4080 Super
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 3.41 GB
- OS
- Ubuntu 22.04
- Driver
- 572.83
- CUDA
- 12.8
- Power draw
- 223.8 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.47 · Ubuntu 22.04 · CUDA 12.8 · 16384 ctx
370.71 tok/s
Decode
1,429.25 tok/s
Prefill
0.63 s
TTFT
3.41 GB
VRAM
—
MTP
223.8 W
Power draw
L2 batch seed 2026-10-19: vLLM on hw_id=20 running model_id=51 at Q4_K_S