Arao AI
Back to search results

Qwen3.8-9B · IQ2_M

Start a discussion
NVIDIA RTX 508016GBStrata v0.52L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.8-9B (IQ2_M) on NVIDIA RTX 5080 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

294.71 tok/s

Decode

Decode speed

1,507.15 tok/s

Prefill

Prefill speed

0.68 s

TTFT

Time to first token

11.93 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. vLLM · Q4_K_M Decode 152.58 · Prefill 685.84 ·
  2. Strata · IQ2_M (current)Decode 294.71 · Prefill 1507.15 ·
  3. Strata · IQ3_XS Decode 265.22 · Prefill 1010.61 ·
  4. llama.cpp · IQ4_XS Decode 97.14 · Prefill 496.38 ·
  5. llama.cpp · Q3_K_M Decode 108.92 · Prefill 455.22 ·
  6. vLLM · IQ2_M Decode 131.31 · Prefill 559.09 ·

Core figures

Decode (avg)
294.71 tok/s
Prefill (avg)
1,507.15 tok/s
TTFT (avg)
0.68 s
VRAM (avg)
11.93 GB
MTP acceptance rate
0.73
TTFB
2.36 GB
Power draw
319 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.8-9B
Quantization
IQ2_M
Framework
Strata
Version
v0.52
Context length
16384 tokens
Batch size
256
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
NVIDIA RTX 5080
Nominal VRAM
16 GB
Measured VRAM (avg)
11.93 GB
OS
Ubuntu 22.04
Driver
570.86
CUDA
13.0
Power draw
319 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

    v0.52 · Ubuntu 22.04 · CUDA 13.0 · 16384 ctx

    294.71 tok/s

    Decode

    1,507.15 tok/s

    Prefill

    0.68 s

    TTFT

    11.93 GB

    VRAM

    0.73

    MTP

    319 W

    Power draw

    L2 batch seed 2026-10-18: Strata on hw_id=14 running model_id=52 at IQ2_M