Arao AI
Back to search results

DeepSeek-R1-Distill-Qwen-14B · Q5_K_M

Start a discussion
Apple M2 UltraOllama v0.52L2 Cross-framework verified

This page aggregates 1 real-world runs of DeepSeek-R1-Distill-Qwen-14B (Q5_K_M) on Apple M2 Ultra with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

66.35 tok/s

Decode

Decode speed

310.63 tok/s

Prefill

Prefill speed

0.56 s

TTFT

Time to first token

29.44 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 · Q4_K_S Decode 92.27 · Prefill 397.78 ·
  2. Ollama · Q3_K_S Decode 106.35 · Prefill 407.93 ·
  3. Ollama · Q5_K_M (current)Decode 66.35 · Prefill 310.63 ·

Core figures

Decode (avg)
66.35 tok/s
Prefill (avg)
310.63 tok/s
TTFT (avg)
0.56 s
VRAM (avg)
29.44 GB
MTP acceptance rate
—
TTFB
0.53 GB
Power draw
142.2 W

Configuration

Member-level fields are taken from the most recent run

Model
DeepSeek-R1-Distill-Qwen-14B
Quantization
Q5_K_M
Framework
Ollama
Version
v0.52
Context length
2048 tokens
Batch size
512
GPU layers
99
Flash Attention
On

Hardware

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

GPU
Apple M2 Ultra
Measured VRAM (avg)
29.44 GB
OS
macOS 26.1
Power draw
142.2 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

    v0.52 · macOS 26.1 · 2048 ctx

    66.35 tok/s

    Decode

    310.63 tok/s

    Prefill

    0.56 s

    TTFT

    29.44 GB

    VRAM

    —

    MTP

    142.2 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=103 running model_id=71 at Q5_K_M