Back to search results
Qwen3-Coder-Next · IQ2_XS
NVIDIA DGX Spark128GBStrata v0.50L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-Coder-Next (IQ2_XS) on NVIDIA DGX Spark with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
259.54 tok/s
Decode
Decode speed
1,190.55 tok/s
Prefill
Prefill speed
1.7 s
TTFT
Time to first token
1.05 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- Ollama · Q3_K_L Decode 131.46 · Prefill 705.73 ·
- Ollama · Q4_K_S Decode 128.78 · Prefill 450.1 ·
- Strata · IQ2_M Decode 261.64 · Prefill 916.28 ·
- Strata · IQ2_XS (current)Decode 259.54 · Prefill 1190.55 ·
Core figures
- Decode (avg)
- 259.54 tok/s
- Prefill (avg)
- 1,190.55 tok/s
- TTFT (avg)
- 1.7 s
- VRAM (avg)
- 1.05 GB
- MTP acceptance rate
- 0.75
- TTFB
- 2.08 GB
- Power draw
- 271.4 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-Coder-Next
- Quantization
- IQ2_XS
- Framework
- Strata
- Version
- v0.50
- Context length
- 2048 tokens
- Batch size
- 1024
- GPU layers
- 8
- 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)
- 1.05 GB
- OS
- Ubuntu 24.04
- Driver
- 565.57
- CUDA
- 12.8
- Power draw
- 271.4 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.50 · Ubuntu 24.04 · CUDA 12.8 · 2048 ctx
259.54 tok/s
Decode
1,190.55 tok/s
Prefill
1.7 s
TTFT
1.05 GB
VRAM
0.75
MTP
271.4 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=54 running model_id=58 at IQ2_XS