Back to search results
Qwen3.5-4B · IQ2_XS
NVIDIA DGX Spark128GBOllama v0.54L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-4B (IQ2_XS) on NVIDIA DGX Spark with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
258.67 tok/s
Decode
Decode speed
1,172.95 tok/s
Prefill
Prefill speed
2.49 s
TTFT
Time to first token
6.13 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- vLLM · IQ1_S Decode 306.37 · Prefill 1243.41 ·
- Ollama · IQ2_XS (current)Decode 258.67 · Prefill 1172.95 ·
- vLLM · Q2_K Decode 266.26 · Prefill 1108.22 ·
- vLLM · Q3_K_L Decode 219.42 · Prefill 756.56 ·
Core figures
- Decode (avg)
- 258.67 tok/s
- Prefill (avg)
- 1,172.95 tok/s
- TTFT (avg)
- 2.49 s
- VRAM (avg)
- 6.13 GB
- MTP acceptance rate
- —
- TTFB
- 2.07 GB
- Power draw
- 170.2 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-4B
- Quantization
- IQ2_XS
- Framework
- Ollama
- Version
- v0.54
- 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 DGX Spark
- Nominal VRAM
- 128 GB
- Measured VRAM (avg)
- 6.13 GB
- OS
- Windows 11 23H2
- Driver
- 560.94
- CUDA
- 12.4
- Power draw
- 170.2 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.54 · Windows 11 23H2 · CUDA 12.4 · 2048 ctx
258.67 tok/s
Decode
1,172.95 tok/s
Prefill
2.49 s
TTFT
6.13 GB
VRAM
—
MTP
170.2 W
Power draw
L2 batch seed 2026-10-16: Ollama on hw_id=54 running model_id=48 at IQ2_XS