Back to search results
Qwen3.5-4B · Q2_K
NVIDIA RTX 408016GBvLLM v0.32L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-4B (Q2_K) on NVIDIA RTX 4080 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
151.45 tok/s
Decode
Decode speed
529.44 tok/s
Prefill
Prefill speed
2.31 s
TTFT
Time to first token
6.72 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- Ollama · IQ2_XS Decode 194.9 · Prefill 903.61 ·
- Strata · Q6_K Decode 181.02 · Prefill 665.46 ·
- vLLM · Q2_K (current)Decode 151.45 · Prefill 529.44 ·
- vLLM · Q3_K_M Decode 130.67 · Prefill 528.13 ·
- Ollama · Q4_K_M Decode 95.12 · Prefill 401.62 ·
Core figures
- Decode (avg)
- 151.45 tok/s
- Prefill (avg)
- 529.44 tok/s
- TTFT (avg)
- 2.31 s
- VRAM (avg)
- 6.72 GB
- MTP acceptance rate
- —
- TTFB
- 1.21 GB
- Power draw
- 341 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-4B
- Quantization
- Q2_K
- Framework
- vLLM
- Version
- v0.32
- 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 4080
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 6.72 GB
- OS
- Windows 11 23H2
- Driver
- 570.86
- CUDA
- 12.4
- Power draw
- 341 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.32 · Windows 11 23H2 · CUDA 12.4 · 32768 ctx
151.45 tok/s
Decode
529.44 tok/s
Prefill
2.31 s
TTFT
6.72 GB
VRAM
—
MTP
341 W
Power draw
L2 batch seed 2026-10-13: vLLM on hw_id=41 running model_id=48 at Q2_K