Back to search results
Qwen3.5-4B · Q3_K_L
NVIDIA RTX 4080 Super16GBOllama v0.40L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-4B (Q3_K_L) on NVIDIA RTX 4080 Super with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
202.33 tok/s
Decode
Decode speed
955.67 tok/s
Prefill
Prefill speed
0.69 s
TTFT
Time to first token
8.15 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- vLLM · Q5_K_M Decode 152.06 · Prefill 772.68 ·
- Ollama · Q3_K_L (current)Decode 202.33 · Prefill 955.67 ·
Core figures
- Decode (avg)
- 202.33 tok/s
- Prefill (avg)
- 955.67 tok/s
- TTFT (avg)
- 0.69 s
- VRAM (avg)
- 8.15 GB
- MTP acceptance rate
- —
- TTFB
- 1.62 GB
- Power draw
- 291.2 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-4B
- Quantization
- Q3_K_L
- Framework
- Ollama
- Version
- v0.40
- Context length
- 4096 tokens
- Batch size
- 512
- GPU layers
- 99
- 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)
- 8.15 GB
- OS
- Ubuntu 24.04
- Driver
- 572.83
- CUDA
- 12.6
- Power draw
- 291.2 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.40 · Ubuntu 24.04 · CUDA 12.6 · 4096 ctx
202.33 tok/s
Decode
955.67 tok/s
Prefill
0.69 s
TTFT
8.15 GB
VRAM
—
MTP
291.2 W
Power draw
L2 batch seed 2026-10-18: Ollama on hw_id=20 running model_id=48 at Q3_K_L