Back to search results
Qwen3.5-4B · IQ3_S
NVIDIA RTX 308010GBOllama v0.43L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-4B (IQ3_S) on NVIDIA RTX 3080 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
92.66 tok/s
Decode
Decode speed
391.24 tok/s
Prefill
Prefill speed
2.41 s
TTFT
Time to first token
7.64 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- vLLM · Q5_K_M Decode 82.42 · Prefill 333.84 ·
- Ollama · IQ2_M Decode 105.52 · Prefill 563.01 ·
- Ollama · IQ3_S (current)Decode 92.66 · Prefill 391.24 ·
Core figures
- Decode (avg)
- 92.66 tok/s
- Prefill (avg)
- 391.24 tok/s
- TTFT (avg)
- 2.41 s
- VRAM (avg)
- 7.64 GB
- MTP acceptance rate
- —
- TTFB
- 0.74 GB
- Power draw
- 266.4 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-4B
- Quantization
- IQ3_S
- Framework
- Ollama
- Version
- v0.43
- Context length
- 2048 tokens
- Batch size
- 256
- GPU layers
- 99
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 3080
- Nominal VRAM
- 10 GB
- Measured VRAM (avg)
- 7.64 GB
- OS
- Ubuntu 24.04
- Driver
- 555.85
- CUDA
- 12.4
- Power draw
- 266.4 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.43 · Ubuntu 24.04 · CUDA 12.4 · 2048 ctx
92.66 tok/s
Decode
391.24 tok/s
Prefill
2.41 s
TTFT
7.64 GB
VRAM
—
MTP
266.4 W
Power draw
L2 batch seed 2026-10-13: Ollama on hw_id=44 running model_id=48 at IQ3_S