Arao AI
Back to search results

Qwen3-1.7B · Q4_K_M

Start a discussion
Apple M1vLLM v0.23L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-1.7B (Q4_K_M) on Apple M1 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

84.3 tok/s

Decode

Decode speed

383.2 tok/s

Prefill

Prefill speed

0.81 s

TTFT

Time to first token

5.03 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

2 days ago

Last verified

Performance

  1. llama.cpp · IQ3_S Decode 97.72 · Prefill 393.93 ·
  2. llama.cpp · Q5_K_M Decode 75.84 · Prefill 355.79 ·
  3. vLLM · Q4_K_M (current)Decode 84.3 · Prefill 383.2 ·
  4. vLLM · Q6_K Decode 72.53 · Prefill 321.64 ·

Core figures

Decode (avg)
84.3 tok/s
Prefill (avg)
383.2 tok/s
TTFT (avg)
0.81 s
VRAM (avg)
5.03 GB
MTP acceptance rate
—
TTFB
0.67 GB
Power draw
52 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-1.7B
Quantization
Q4_K_M
Framework
vLLM
Version
v0.23
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 M1
Measured VRAM (avg)
5.03 GB
OS
macOS 15.0
Driver
Apple M1
CUDA
N/A
Power draw
52 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-16

    v0.23 · macOS 15.0 · CUDA N/A · 16384 ctx

    84.3 tok/s

    Decode

    383.2 tok/s

    Prefill

    0.81 s

    TTFT

    5.03 GB

    VRAM

    —

    MTP

    52 W

    Power draw

    L2 batch seed 2026-10-16: vLLM on hw_id=99 running model_id=55 at Q4_K_M