Back to search results
Qwen3.5-4B · IQ2_M
NVIDIA RTX 308010GBOllama v0.45L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-4B (IQ2_M) on NVIDIA RTX 3080 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
105.52 tok/s
Decode
Decode speed
563.01 tok/s
Prefill
Prefill speed
0.23 s
TTFT
Time to first token
6.47 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 (current)Decode 105.52 · Prefill 563.01 ·
- Ollama · IQ3_S Decode 92.66 · Prefill 391.24 ·
Core figures
- Decode (avg)
- 105.52 tok/s
- Prefill (avg)
- 563.01 tok/s
- TTFT (avg)
- 0.23 s
- VRAM (avg)
- 6.47 GB
- MTP acceptance rate
- —
- TTFB
- 0.84 GB
- Power draw
- 308.6 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-4B
- Quantization
- IQ2_M
- Framework
- Ollama
- Version
- v0.45
- Context length
- 2048 tokens
- Batch size
- 256
- GPU layers
- 28
- 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)
- 6.47 GB
- OS
- Ubuntu 22.04
- Driver
- 555.85
- CUDA
- 12.4
- Power draw
- 308.6 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.45 · Ubuntu 22.04 · CUDA 12.4 · 2048 ctx
105.52 tok/s
Decode
563.01 tok/s
Prefill
0.23 s
TTFT
6.47 GB
VRAM
—
MTP
308.6 W
Power draw
L2 batch seed 2026-10-13: Ollama on hw_id=44 running model_id=48 at IQ2_M