Arao AI
Back to search results

Qwen3.5-0.8B · IQ2_M

Start a discussion
NVIDIA H100 80GB HBM380GBvLLM v0.53L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-0.8B (IQ2_M) on NVIDIA H100 80GB HBM3 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

294.68 tok/s

Decode

Decode speed

1,324.31 tok/s

Prefill

Prefill speed

0.41 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

17 days ago

Last verified

Performance

  1. llama.cpp · Q4_K_S Decode 340.19 · Prefill 1569.8 ·
  2. vLLM · IQ2_M (current)Decode 294.68 · Prefill 1324.31 ·
  3. vLLM · Q3_K_S Decode 355.68 · Prefill 1952.96 ·

Core figures

Decode (avg)
294.68 tok/s
Prefill (avg)
1,324.31 tok/s
TTFT (avg)
0.41 s
VRAM (avg)
2.97 GB
MTP acceptance rate
—
TTFB
2.36 GB
Power draw
630.6 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
IQ2_M
Framework
vLLM
Version
v0.53
Context length
8192 tokens
Batch size
16
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
NVIDIA H100 80GB HBM3
Nominal VRAM
80 GB
Measured VRAM (avg)
2.97 GB
OS
Ubuntu 24.04
Driver
572.83
CUDA
12.8
Power draw
630.6 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-19

    v0.53 · Ubuntu 24.04 · CUDA 12.8 · 8192 ctx

    294.68 tok/s

    Decode

    1,324.31 tok/s

    Prefill

    0.41 s

    TTFT

    2.97 GB

    VRAM

    —

    MTP

    630.6 W

    Power draw

    L2 batch seed 2026-10-19: vLLM on hw_id=55 running model_id=51 at IQ2_M