Arao AI
Back to search results

Qwen3-8B · IQ2_M

Start a discussion
AMD Radeon RX 7900 XTX24GBStrata v0.51L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-8B (IQ2_M) on AMD Radeon RX 7900 XTX with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

148.41 tok/s

Decode

Decode speed

586.66 tok/s

Prefill

Prefill speed

2.3 s

TTFT

Time to first token

10.84 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. Ollama · IQ3_XS Decode 90.61 · Prefill 409.37 ·
  2. Strata · IQ2_M (current)Decode 148.41 · Prefill 586.66 ·
  3. vLLM · IQ2_M Decode 141.39 · Prefill 740.19 ·
  4. Ollama · Q5_K_S Decode 83.18 · Prefill 356.29 ·
  5. Strata · Q8_0 Decode 88.6 · Prefill 455.19 ·

Core figures

Decode (avg)
148.41 tok/s
Prefill (avg)
586.66 tok/s
TTFT (avg)
2.3 s
VRAM (avg)
10.84 GB
MTP acceptance rate
0.71
TTFB
1.19 GB
Power draw
258.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-8B
Quantization
IQ2_M
Framework
Strata
Version
v0.51
Context length
4096 tokens
Batch size
1024
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
AMD Radeon RX 7900 XTX
Nominal VRAM
24 GB
Measured VRAM (avg)
10.84 GB
OS
Ubuntu 22.04
Driver
amdgpu 6.12
CUDA
12.6
Power draw
258.2 W

Sources & evidence

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

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

    v0.51 · Ubuntu 22.04 · CUDA 12.6 · 4096 ctx

    148.41 tok/s

    Decode

    586.66 tok/s

    Prefill

    2.3 s

    TTFT

    10.84 GB

    VRAM

    0.71

    MTP

    258.2 W

    Power draw

    L2 batch seed 2026-10-18: Strata on hw_id=11 running model_id=53 at IQ2_M