Back to search results
Qwen2.5-0.5B-Instruct · IQ4_XS
NVIDIA DGX Spark128GBOllama v0.40L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen2.5-0.5B-Instruct (IQ4_XS) on NVIDIA DGX Spark with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
345.19 tok/s
Decode
Decode speed
1,510.37 tok/s
Prefill
Prefill speed
1.21 s
TTFT
Time to first token
2.88 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- llama.cpp · IQ2_XS Decode 344.66 · Prefill 1710.46 ·
- Strata · IQ2_XS Decode 295.77 · Prefill 1437.09 ·
- Strata · Q5_K_M Decode 294.11 · Prefill 1222.22 ·
- Ollama · IQ4_XS (current)Decode 345.19 · Prefill 1510.37 ·
- Ollama · Q6_K Decode 298.04 · Prefill 1558.09 ·
Core figures
- Decode (avg)
- 345.19 tok/s
- Prefill (avg)
- 1,510.37 tok/s
- TTFT (avg)
- 1.21 s
- VRAM (avg)
- 2.88 GB
- MTP acceptance rate
- —
- TTFB
- 2.76 GB
- Power draw
- 258.8 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen2.5-0.5B-Instruct
- Quantization
- IQ4_XS
- Framework
- Ollama
- Version
- v0.40
- Context length
- 16384 tokens
- Batch size
- 256
- GPU layers
- 20
- 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)
- 2.88 GB
- OS
- Ubuntu 24.04
- Driver
- 560.94
- CUDA
- 12.8
- Power draw
- 258.8 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.40 · Ubuntu 24.04 · CUDA 12.8 · 16384 ctx
345.19 tok/s
Decode
1,510.37 tok/s
Prefill
1.21 s
TTFT
2.88 GB
VRAM
—
MTP
258.8 W
Power draw
L2 batch seed 2026-10-13: Ollama on hw_id=54 running model_id=59 at IQ4_XS