Back to search results
Qwen3.5-0.8B · IQ4_XS
NVIDIA DGX Spark128GBOllama v0.53L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-0.8B (IQ4_XS) on NVIDIA DGX Spark with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
338.64 tok/s
Decode
Decode speed
1,719.5 tok/s
Prefill
Prefill speed
1.64 s
TTFT
Time to first token
3.34 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- vLLM · IQ2_XS Decode 310.29 · Prefill 1000.44 ·
- Ollama · IQ2_XS Decode 348.98 · Prefill 1689.57 ·
- Ollama · Q3_K_M Decode 387.92 · Prefill 1612.07 ·
- Ollama · IQ3_XS Decode 391.28 · Prefill 1950.82 ·
- Ollama · IQ4_XS (current)Decode 338.64 · Prefill 1719.5 ·
Core figures
- Decode (avg)
- 338.64 tok/s
- Prefill (avg)
- 1,719.5 tok/s
- TTFT (avg)
- 1.64 s
- VRAM (avg)
- 3.34 GB
- MTP acceptance rate
- —
- TTFB
- 2.71 GB
- Power draw
- 217 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-0.8B
- Quantization
- IQ4_XS
- Framework
- Ollama
- Version
- v0.53
- Context length
- 32768 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)
- 3.34 GB
- OS
- Ubuntu 24.04
- Driver
- 570.86
- CUDA
- 12.8
- Power draw
- 217 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.53 · Ubuntu 24.04 · CUDA 12.8 · 32768 ctx
338.64 tok/s
Decode
1,719.5 tok/s
Prefill
1.64 s
TTFT
3.34 GB
VRAM
—
MTP
217 W
Power draw
L2 batch seed 2026-10-13: Ollama on hw_id=54 running model_id=51 at IQ4_XS