Back to search results
Qwen2.5-0.5B-Instruct · IQ2_XS
NVIDIA DGX Spark128GBStrata v0.51L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen2.5-0.5B-Instruct (IQ2_XS) on NVIDIA DGX Spark with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
295.77 tok/s
Decode
Decode speed
1,437.09 tok/s
Prefill
Prefill speed
1.77 s
TTFT
Time to first token
2.6 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- llama.cpp · IQ2_XS Decode 344.66 · Prefill 1710.46 ·
- Strata · IQ2_XS (current)Decode 295.77 · Prefill 1437.09 ·
- Strata · Q5_K_M Decode 294.11 · Prefill 1222.22 ·
- Ollama · IQ4_XS Decode 345.19 · Prefill 1510.37 ·
- Ollama · Q6_K Decode 298.04 · Prefill 1558.09 ·
Core figures
- Decode (avg)
- 295.77 tok/s
- Prefill (avg)
- 1,437.09 tok/s
- TTFT (avg)
- 1.77 s
- VRAM (avg)
- 2.6 GB
- MTP acceptance rate
- 0.67
- TTFB
- 2.37 GB
- Power draw
- 197.6 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen2.5-0.5B-Instruct
- Quantization
- IQ2_XS
- Framework
- Strata
- Version
- v0.51
- Context length
- 16384 tokens
- Batch size
- 512
- GPU layers
- 12
- Flash Attention
- Off
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)
- 2.6 GB
- OS
- Windows 11 23H2
- Driver
- 555.85
- CUDA
- 12.4
- Power draw
- 197.6 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.51 · Windows 11 23H2 · CUDA 12.4 · 16384 ctx
295.77 tok/s
Decode
1,437.09 tok/s
Prefill
1.77 s
TTFT
2.6 GB
VRAM
0.67
MTP
197.6 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=54 running model_id=59 at IQ2_XS