Arao AI
Back to search results

DeepSeek-R1-Distill-Qwen-14B · Q2_K

Start a discussion
Apple M5 Pro64GBllama.cpp v0.34L2 Cross-framework verified

This page aggregates 1 real-world runs of DeepSeek-R1-Distill-Qwen-14B (Q2_K) on Apple M5 Pro with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

127.36 tok/s

Decode

Decode speed

409.89 tok/s

Prefill

Prefill speed

1.67 s

TTFT

Time to first token

18.27 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. llama.cpp · Q2_K (current)Decode 127.36 · Prefill 409.89 ·

Core figures

Decode (avg)
127.36 tok/s
Prefill (avg)
409.89 tok/s
TTFT (avg)
1.67 s
VRAM (avg)
18.27 GB
MTP acceptance rate
—
TTFB
1.02 GB
Power draw
129.9 W

Configuration

Member-level fields are taken from the most recent run

Model
DeepSeek-R1-Distill-Qwen-14B
Quantization
Q2_K
Framework
llama.cpp
Version
v0.34
Context length
2048 tokens
Batch size
256
GPU layers
28
Flash Attention
Off

Hardware

Nominal and measured figures are shown side by side; whether it runs is the reader's call

GPU
Apple M5 Pro
Nominal VRAM
64 GB
Measured VRAM (avg)
18.27 GB
OS
macOS 15.0
Driver
Apple M5 Pro
CUDA
N/A
Power draw
129.9 W

Sources & evidence

1 measured records in total, each traceable to its original source

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-13

    v0.34 · macOS 15.0 · CUDA N/A · 2048 ctx

    127.36 tok/s

    Decode

    409.89 tok/s

    Prefill

    1.67 s

    TTFT

    18.27 GB

    VRAM

    —

    MTP

    129.9 W

    Power draw

    L2 batch seed 2026-10-13: llama.cpp on hw_id=27 running model_id=71 at Q2_K