Back to search results
DeepSeek-R1-Distill-Qwen-14B · Q4_K_M
Apple M4 Pro64GBvLLM v0.52L2 Cross-framework verified
This page aggregates 1 real-world runs of DeepSeek-R1-Distill-Qwen-14B (Q4_K_M) on Apple M4 Pro with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
76.77 tok/s
Decode
Decode speed
324.87 tok/s
Prefill
Prefill speed
1.38 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_S Decode 87.73 · Prefill 414.18 ·
- vLLM · Q4_K_M (current)Decode 76.77 · Prefill 324.87 ·
- Strata · IQ3_S Decode 124.6 · Prefill 542.9 ·
Core figures
- Decode (avg)
- 76.77 tok/s
- Prefill (avg)
- 324.87 tok/s
- TTFT (avg)
- 1.38 s
- VRAM (avg)
- 26.21 GB
- MTP acceptance rate
- —
- TTFB
- 0.61 GB
- Power draw
- 80.4 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
- v0.52
- Context length
- 8192 tokens
- Batch size
- 32
- 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
- Apple M4 Pro
- Nominal VRAM
- 64 GB
- Measured VRAM (avg)
- 26.21 GB
- OS
- macOS 15.0
- Driver
- Apple M4 Pro
- CUDA
- N/A
- Power draw
- 80.4 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.52 · macOS 15.0 · CUDA N/A · 8192 ctx
76.77 tok/s
Decode
324.87 tok/s
Prefill
1.38 s
TTFT
26.21 GB
VRAM
—
MTP
80.4 W
Power draw
L2 batch seed 2026-10-13: vLLM on hw_id=25 running model_id=71 at Q4_K_M