Arao AI
Back to search results

Qwen3.5-0.8B · FP16

Start a discussion
Apple M5 Max128GBStrata v0.51L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-0.8B (FP16) on Apple M5 Max with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

330.86 tok/s

Decode

Decode speed

1,157.2 tok/s

Prefill

Prefill speed

1.56 s

TTFT

Time to first token

5.21 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

2 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 (current)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 Decode 308.09 · Prefill 1499.86 ·

Core figures

Decode (avg)
330.86 tok/s
Prefill (avg)
1,157.2 tok/s
TTFT (avg)
1.56 s
VRAM (avg)
5.21 GB
MTP acceptance rate
0.77
TTFB
2.65 GB
Power draw
254.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
FP16
Framework
Strata
Version
v0.51
Context length
8192 tokens
Batch size
256
GPU layers
12
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)
5.21 GB
OS
Windows 11 23H2
Driver
560.94
CUDA
12.6
Power draw
254.2 W

Sources & evidence

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

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

    v0.51 · Windows 11 23H2 · CUDA 12.6 · 8192 ctx

    330.86 tok/s

    Decode

    1,157.2 tok/s

    Prefill

    1.56 s

    TTFT

    5.21 GB

    VRAM

    0.77

    MTP

    254.2 W

    Power draw

    L2 batch seed 2026-10-16: Strata on hw_id=28 running model_id=51 at FP16