Arao AI
Back to search results

Qwen3.8-27B · IQ2_M

Start a discussion
Apple M4 Max128GBStrata v0.32L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.8-27B (IQ2_M) on Apple M4 Max with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

265.43 tok/s

Decode

Decode speed

1,342.3 tok/s

Prefill

Prefill speed

1.28 s

TTFT

Time to first token

31.58 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. vLLM · Q5_K_S Decode 122.2 · Prefill 481.39 ·
  2. Strata · IQ2_M (current)Decode 265.43 · Prefill 1342.3 ·
  3. Strata · IQ3_S Decode 228.14 · Prefill 1118.4 ·
  4. llama.cpp · Q4_K_M Decode 26 · Prefill 195 ·

Core figures

Decode (avg)
265.43 tok/s
Prefill (avg)
1,342.3 tok/s
TTFT (avg)
1.28 s
VRAM (avg)
31.58 GB
MTP acceptance rate
0.66
TTFB
2.12 GB
Power draw
44 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.8-27B
Quantization
IQ2_M
Framework
Strata
Version
v0.32
Context length
8192 tokens
Batch size
512
GPU layers
12
Flash Attention
Off

Hardware

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

GPU
Apple M4 Max
Nominal VRAM
128 GB
Measured VRAM (avg)
31.58 GB
OS
macOS 15.0
Driver
Apple M4 Max
CUDA
N/A
Power draw
44 W

Get started

Original model resources

Base model resources may not match this quantization. Use the verified deployment weights above when available.

Sources & evidence

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

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

    v0.32 · macOS 15.0 · CUDA N/A · 8192 ctx

    265.43 tok/s

    Decode

    1,342.3 tok/s

    Prefill

    1.28 s

    TTFT

    31.58 GB

    VRAM

    0.66

    MTP

    44 W

    Power draw

    L2 batch seed 2026-10-10: Strata on hw_id=26 running model_id=5 at IQ2_M