Back to search results
DeepSeek-R1-Distill-Qwen-14B · Q4_K_M
NVIDIA DGX Spark128GBvLLM v0.50L2 Cross-framework verified
This page aggregates 1 real-world runs of DeepSeek-R1-Distill-Qwen-14B (Q4_K_M) on NVIDIA DGX Spark with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
106.85 tok/s
Decode
Decode speed
369.96 tok/s
Prefill
Prefill speed
0.89 s
TTFT
Time to first token
26.21 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- vLLM · Q3_K_L Decode 126.48 · Prefill 583.23 ·
- vLLM · Q4_K_M (current)Decode 106.85 · Prefill 369.96 ·
- Ollama · IQ2_M Decode 126.86 · Prefill 519.13 ·
Core figures
- Decode (avg)
- 106.85 tok/s
- Prefill (avg)
- 369.96 tok/s
- TTFT (avg)
- 0.89 s
- VRAM (avg)
- 26.21 GB
- MTP acceptance rate
- —
- TTFB
- 0.85 GB
- Power draw
- 255 W
Configuration
Member-level fields are taken from the most recent run
- Model
- DeepSeek-R1-Distill-Qwen-14B
- Quantization
- Q4_K_M
- Framework
- vLLM
- Version
- v0.50
- Context length
- 8192 tokens
- Batch size
- 16
- GPU layers
- 999
- 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)
- 26.21 GB
- OS
- Ubuntu 24.04
- Driver
- 570.86
- CUDA
- 12.8
- Power draw
- 255 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.50 · Ubuntu 24.04 · CUDA 12.8 · 8192 ctx
106.85 tok/s
Decode
369.96 tok/s
Prefill
0.89 s
TTFT
26.21 GB
VRAM
—
MTP
255 W
Power draw
L2 batch seed 2026-10-13: vLLM on hw_id=54 running model_id=71 at Q4_K_M