Back to search results
DeepSeek-R1-Distill-Qwen-14B · Q4_K_M
Apple M5 Max128GBvLLM v0.28L2 Cross-framework verified
This page aggregates 1 real-world runs of DeepSeek-R1-Distill-Qwen-14B (Q4_K_M) on Apple M5 Max with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
134.81 tok/s
Decode
Decode speed
469.71 tok/s
Prefill
Prefill speed
0.35 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
- llama.cpp · IQ1_S Decode 202.22 · Prefill 672.97 ·
- vLLM · Q4_K_M (current)Decode 134.81 · Prefill 469.71 ·
Core figures
- Decode (avg)
- 134.81 tok/s
- Prefill (avg)
- 469.71 tok/s
- TTFT (avg)
- 0.35 s
- VRAM (avg)
- 26.21 GB
- MTP acceptance rate
- —
- TTFB
- 1.08 GB
- Power draw
- 91.2 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
- v0.28
- Context length
- 16384 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 M5 Max
- Nominal VRAM
- 128 GB
- Measured VRAM (avg)
- 26.21 GB
- OS
- macOS 15.0
- Driver
- Apple M5 Max
- CUDA
- N/A
- Power draw
- 91.2 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.28 · macOS 15.0 · CUDA N/A · 16384 ctx
134.81 tok/s
Decode
469.71 tok/s
Prefill
0.35 s
TTFT
26.21 GB
VRAM
—
MTP
91.2 W
Power draw
L2 batch seed 2026-10-13: vLLM on hw_id=28 running model_id=71 at Q4_K_M