Back to search results
DeepSeek-R1-Distill-Qwen-14B · Q3_K_M
NVIDIA RTX 409024GBllama.cpp v0.47L2 Cross-framework verified
This page aggregates 1 real-world runs of DeepSeek-R1-Distill-Qwen-14B (Q3_K_M) on NVIDIA RTX 4090 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
122.06 tok/s
Decode
Decode speed
409.59 tok/s
Prefill
Prefill speed
2.2 s
TTFT
Time to first token
22.09 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
17 days ago
Last verified
Performance
- llama.cpp · Q3_K_M (current)Decode 122.06 · Prefill 409.59 ·
- vLLM · IQ2_M Decode 163.66 · Prefill 743.62 ·
- Ollama · Q3_K_L Decode 117.29 · Prefill 610.83 ·
- vLLM · Q5_K_M Decode 82.4 · Prefill 618 ·
- vLLM · Q4_K_M Decode 100.8 · Prefill 756 ·
- llama.cpp · Q5_K_M Decode 75.6 · Prefill 567 ·
- llama.cpp · Q4_K_M Decode 92.5 · Prefill 693.8 ·
Core figures
- Decode (avg)
- 122.06 tok/s
- Prefill (avg)
- 409.59 tok/s
- TTFT (avg)
- 2.2 s
- VRAM (avg)
- 22.09 GB
- MTP acceptance rate
- —
- TTFB
- 0.98 GB
- Power draw
- 306.5 W
Configuration
Member-level fields are taken from the most recent run
- Model
- DeepSeek-R1-Distill-Qwen-14B
- Quantization
- Q3_K_M
- Framework
- llama.cpp
- Version
- v0.47
- Context length
- 2048 tokens
- Batch size
- 256
- GPU layers
- 33
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 4090
- Nominal VRAM
- 24 GB
- Measured VRAM (avg)
- 22.09 GB
- OS
- Ubuntu 24.04
- Driver
- 560.94
- CUDA
- 12.8
- Power draw
- 306.5 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.47 · Ubuntu 24.04 · CUDA 12.8 · 2048 ctx
122.06 tok/s
Decode
409.59 tok/s
Prefill
2.2 s
TTFT
22.09 GB
VRAM
—
MTP
306.5 W
Power draw
L2 batch seed 2026-10-19: llama.cpp on hw_id=1 running model_id=71 at Q3_K_M