Arao AI
Back to search results

DeepSeek-R1-Distill-Qwen-14B · Q2_K

Start a discussion
Apple M5 Ultra512GBOllama v0.24L2 Cross-framework verified

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

118.32 tok/s

Decode

Decode speed

453.53 tok/s

Prefill

Prefill speed

0.83 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

16 days ago

Last verified

Performance

  1. llama.cpp · Q5_K_M Decode 77.61 · Prefill 409.9 ·
  2. Ollama · Q2_K (current)Decode 118.32 · Prefill 453.53 ·
  3. Ollama · Q5_K_M Decode 65.66 · Prefill 313.69 ·

Core figures

Decode (avg)
118.32 tok/s
Prefill (avg)
453.53 tok/s
TTFT (avg)
0.83 s
VRAM (avg)
18.27 GB
MTP acceptance rate
—
TTFB
0.95 GB
Power draw
92.4 W

Configuration

Member-level fields are taken from the most recent run

Model
DeepSeek-R1-Distill-Qwen-14B
Quantization
Q2_K
Framework
Ollama
Version
v0.24
Context length
16384 tokens
Batch size
256
GPU layers
20
Flash Attention
On

Hardware

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

GPU
Apple M5 Ultra
Nominal VRAM
512 GB
Measured VRAM (avg)
18.27 GB
OS
macOS 26.1
Power draw
92.4 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-19

    v0.24 · macOS 26.1 · 16384 ctx

    118.32 tok/s

    Decode

    453.53 tok/s

    Prefill

    0.83 s

    TTFT

    18.27 GB

    VRAM

    —

    MTP

    92.4 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=29 running model_id=71 at Q2_K