Back to search results
Qwen3.5-0.8B · Q5_K_M
NVIDIA RTX 408016GBvLLM v0.31L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-0.8B (Q5_K_M) on NVIDIA RTX 4080 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
304.13 tok/s
Decode
Decode speed
1,485.96 tok/s
Prefill
Prefill speed
0.24 s
TTFT
Time to first token
3.66 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- vLLM · Q3_K_S Decode 378.63 · Prefill 1756.55 ·
- vLLM · Q5_K_M (current)Decode 304.13 · Prefill 1485.96 ·
- Strata · IQ1_S Decode 334.33 · Prefill 1448.23 ·
- Strata · Q8_0 Decode 328.32 · Prefill 1297.3 ·
- vLLM · Q6_K Decode 169.83 · Prefill 688.66 ·
- Strata · Q3_K_S Decode 370.12 · Prefill 1878.16 ·
Core figures
- Decode (avg)
- 304.13 tok/s
- Prefill (avg)
- 1,485.96 tok/s
- TTFT (avg)
- 0.24 s
- VRAM (avg)
- 3.66 GB
- MTP acceptance rate
- —
- TTFB
- 2.43 GB
- Power draw
- 310.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-0.8B
- Quantization
- Q5_K_M
- Framework
- vLLM
- Version
- v0.31
- Context length
- 4096 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 4080
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 3.66 GB
- OS
- Windows 11 23H2
- Driver
- 565.57
- CUDA
- 13.0
- Power draw
- 310.1 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.31 · Windows 11 23H2 · CUDA 13.0 · 4096 ctx
304.13 tok/s
Decode
1,485.96 tok/s
Prefill
0.24 s
TTFT
3.66 GB
VRAM
—
MTP
310.1 W
Power draw
L2 batch seed 2026-10-18: vLLM on hw_id=41 running model_id=51 at Q5_K_M