Arao AI
Back to search results

Qwen3.5-0.8B · IQ1_S

Start a discussion
AMD Radeon RX 907016GBOllama v0.37L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-0.8B (IQ1_S) on AMD Radeon RX 9070 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

353.51 tok/s

Decode

Decode speed

1,875.31 tok/s

Prefill

Prefill speed

2.47 s

TTFT

Time to first token

2.8 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. llama.cpp · Q3_K_S Decode 282.09 · Prefill 1248.73 ·
  2. llama.cpp · Q4_K_M Decode 250.59 · Prefill 955.15 ·
  3. Ollama · IQ1_S (current)Decode 353.51 · Prefill 1875.31 ·
  4. llama.cpp · Q3_K_L Decode 236.42 · Prefill 1273.33 ·
  5. vLLM · IQ1_S Decode 361.98 · Prefill 1724.43 ·
  6. vLLM · IQ2_M Decode 325.3 · Prefill 1252.35 ·

Core figures

Decode (avg)
353.51 tok/s
Prefill (avg)
1,875.31 tok/s
TTFT (avg)
2.47 s
VRAM (avg)
2.8 GB
MTP acceptance rate
—
TTFB
2.83 GB
Power draw
202 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
IQ1_S
Framework
Ollama
Version
v0.37
Context length
8192 tokens
Batch size
512
GPU layers
20
Flash Attention
On

Hardware

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

GPU
AMD Radeon RX 9070
Nominal VRAM
16 GB
Measured VRAM (avg)
2.8 GB
OS
Ubuntu 22.04
Driver
amdgpu 6.11
CUDA
12.8
Power draw
202 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-18

    v0.37 · Ubuntu 22.04 · CUDA 12.8 · 8192 ctx

    353.51 tok/s

    Decode

    1,875.31 tok/s

    Prefill

    2.47 s

    TTFT

    2.8 GB

    VRAM

    —

    MTP

    202 W

    Power draw

    L2 batch seed 2026-10-18: Ollama on hw_id=21 running model_id=51 at IQ1_S