Arao AI
Back to search results

Qwen3.5-0.8B · IQ2_M

Start a discussion
Apple M5 Max128GBStrata v0.31L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-0.8B (IQ2_M) on Apple M5 Max with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

308.09 tok/s

Decode

Decode speed

1,499.86 tok/s

Prefill

Prefill speed

2.05 s

TTFT

Time to first token

2.97 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. Ollama · Q4_K_S Decode 308.8 · Prefill 1388.47 ·
  2. Ollama · Q5_K_M Decode 365.7 · Prefill 1467.25 ·
  3. Strata · FP16 Decode 330.86 · Prefill 1157.2 ·
  4. Strata · Q4_K_M Decode 357.61 · Prefill 1232.58 ·
  5. Ollama · IQ3_S Decode 329.08 · Prefill 1581.37 ·
  6. Ollama · Q2_K Decode 281.81 · Prefill 1519.14 ·
  7. Strata · IQ2_M (current)Decode 308.09 · Prefill 1499.86 ·

Core figures

Decode (avg)
308.09 tok/s
Prefill (avg)
1,499.86 tok/s
TTFT (avg)
2.05 s
VRAM (avg)
2.97 GB
MTP acceptance rate
0.65
TTFB
2.46 GB
Power draw
83.3 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
IQ2_M
Framework
Strata
Version
v0.31
Context length
16384 tokens
Batch size
1024
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 M5 Max
Nominal VRAM
128 GB
Measured VRAM (avg)
2.97 GB
OS
macOS 15.0
Driver
Apple M5 Max
CUDA
N/A
Power draw
83.3 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

    v0.31 · macOS 15.0 · CUDA N/A · 16384 ctx

    308.09 tok/s

    Decode

    1,499.86 tok/s

    Prefill

    2.05 s

    TTFT

    2.97 GB

    VRAM

    0.65

    MTP

    83.3 W

    Power draw

    L2 batch seed 2026-10-13: Strata on hw_id=28 running model_id=51 at IQ2_M