Qwen3.5-4B · IQ2_XS
This page aggregates 2 real-world runs of Qwen3.5-4B (IQ2_XS) on NVIDIA RTX 4080 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
194.9 tok/s
Decode
Decode speed
903.61 tok/s
Prefill
Prefill speed
1.26 s
TTFT
Time to first token
6.13 GB
VRAM
VRAM usage
2
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- Ollama · IQ2_XS (current)Decode 194.9 · Prefill 903.61 ·
- Strata · Q6_K Decode 181.02 · Prefill 665.46 ·
- vLLM · Q2_K 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)
- 194.9 tok/s
- Prefill (avg)
- 903.61 tok/s
- TTFT (avg)
- 1.26 s
- VRAM (avg)
- 6.13 GB
- MTP acceptance rate
- —
- TTFB
- 1.56 GB
- Power draw
- 286.8 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-4B
- Quantization
- IQ2_XS
- Framework
- Ollama
- Version
- v0.31
- Context length
- 32768 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
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 6.13 GB
- OS
- Ubuntu 22.04
- Driver
- 565.57
- CUDA
- 12.6
- Power draw
- 310.5 W
Sources & evidence
2 measured records in total, each traceable to its original source
v0.31 · Ubuntu 22.04 · CUDA 12.6 · 32768 ctx
238.18 tok/s
Decode
1,075.29 tok/s
Prefill
2.13 s
TTFT
6.13 GB
VRAM
—
MTP
310.5 W
Power draw
L2 batch seed 2026-10-18: Ollama on hw_id=41 running model_id=48 at IQ2_XS
v0.27 · Windows 11 23H2 · CUDA 12.6 · 2048 ctx
151.62 tok/s
Decode
731.93 tok/s
Prefill
0.39 s
TTFT
6.13 GB
VRAM
—
MTP
263.1 W
Power draw
L2 batch seed 2026-10-13: Ollama on hw_id=41 running model_id=48 at IQ2_XS