Arao AI
Back to search results

DeepSeek-R1-Distill-Qwen-14B · IQ3_S

Start a discussion
Apple M4 Pro64GBStrata v0.51L2 Cross-framework verified

This page aggregates 1 real-world runs of DeepSeek-R1-Distill-Qwen-14B (IQ3_S) on Apple M4 Pro with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

124.6 tok/s

Decode

Decode speed

542.9 tok/s

Prefill

Prefill speed

0.2 s

TTFT

Time to first token

21.5 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. vLLM · Q3_K_S Decode 87.73 · Prefill 414.18 ·
  2. vLLM · Q4_K_M Decode 76.77 · Prefill 324.87 ·
  3. Strata · IQ3_S (current)Decode 124.6 · Prefill 542.9 ·

Core figures

Decode (avg)
124.6 tok/s
Prefill (avg)
542.9 tok/s
TTFT (avg)
0.2 s
VRAM (avg)
21.5 GB
MTP acceptance rate
0.61
TTFB
1 GB
Power draw
93.6 W

Configuration

Member-level fields are taken from the most recent run

Model
DeepSeek-R1-Distill-Qwen-14B
Quantization
IQ3_S
Framework
Strata
Version
v0.51
Context length
8192 tokens
Batch size
256
GPU layers
15
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)
21.5 GB
OS
macOS 15.0
Driver
Apple M4 Pro
CUDA
N/A
Power draw
93.6 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

    v0.51 · macOS 15.0 · CUDA N/A · 8192 ctx

    124.6 tok/s

    Decode

    542.9 tok/s

    Prefill

    0.2 s

    TTFT

    21.5 GB

    VRAM

    0.61

    MTP

    93.6 W

    Power draw

    L2 batch seed 2026-10-13: Strata on hw_id=25 running model_id=71 at IQ3_S