Arao AI
Back to search results

Qwen3.6-27B · IQ2_M

Start a discussion
NVIDIA RTX 509032GBOllama v0.37L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.6-27B (IQ2_M) on NVIDIA RTX 5090 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

234.19 tok/s

Decode

Decode speed

870.04 tok/s

Prefill

Prefill speed

0.88 s

TTFT

Time to first token

30.4 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. Ollama · IQ2_M (current)Decode 234.19 · Prefill 870.04 ·
  2. llama.cpp · IQ1_S Decode 273.05 · Prefill 882.7 ·

Core figures

Decode (avg)
234.19 tok/s
Prefill (avg)
870.04 tok/s
TTFT (avg)
0.88 s
VRAM (avg)
30.4 GB
MTP acceptance rate
—
TTFB
1.87 GB
Power draw
462.8 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.6-27B
Quantization
IQ2_M
Framework
Ollama
Version
v0.37
Context length
16384 tokens
Batch size
256
GPU layers
33
Flash Attention
On

Hardware

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

GPU
NVIDIA RTX 5090
Nominal VRAM
32 GB
Measured VRAM (avg)
30.4 GB
OS
Ubuntu 24.04
Driver
570.86
CUDA
12.8
Power draw
462.8 W

Get started

Original model resources

Base model resources may not match this quantization. Use the verified deployment weights above when available.

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 24.04 · CUDA 12.8 · 16384 ctx

    234.19 tok/s

    Decode

    870.04 tok/s

    Prefill

    0.88 s

    TTFT

    30.4 GB

    VRAM

    —

    MTP

    462.8 W

    Power draw

    L2 batch seed 2026-10-18: Ollama on hw_id=13 running model_id=6 at IQ2_M