Arao AI
Back to search results

Qwen3.5-27B · IQ1_S

Start a discussion
NVIDIA RTX 309024GBOllama v0.49L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-27B (IQ1_S) on NVIDIA RTX 3090 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

89.8 tok/s

Decode

Decode speed

459.43 tok/s

Prefill

Prefill speed

0.62 s

TTFT

Time to first token

22.8 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

17 days ago

Last verified

Performance

  1. Ollama · IQ1_S (current)Decode 89.8 · Prefill 459.43 ·
  2. llama.cpp · IQ4_XS Decode 91 · Prefill 1085 ·
  3. llama.cpp · Q4_K_M Decode 81 · Prefill 971 ·
  4. llama.cpp · Q5_K_M Decode 92 · Prefill 957 ·
  5. llama.cpp · Q8_0 Decode 68 · Prefill 642 ·
  6. vLLM · IQ4_XS Decode 88 · Prefill 969 ·
  7. vLLM · Q4_K_M Decode 81 · Prefill 868 ·
  8. vLLM · Q5_K_M Decode 79 · Prefill 714 ·
  9. vLLM · Q8_0 Decode 50 · Prefill 591 ·
  10. Ollama · IQ4_XS Decode 103 · Prefill 847 ·
  11. Ollama · Q4_K_M Decode 93 · Prefill 803 ·
  12. Ollama · Q5_K_M Decode 78 · Prefill 912 ·
  13. Ollama · Q8_0 Decode 62 · Prefill 699 ·
  14. Strata · IQ4_XS Decode 138 · Prefill 1557 ·
  15. Strata · Q4_K_M Decode 123 · Prefill 1415 ·
  16. Strata · Q5_K_M Decode 122 · Prefill 1402 ·
  17. Strata · Q8_0 Decode 97 · Prefill 795 ·

Core figures

Decode (avg)
89.8 tok/s
Prefill (avg)
459.43 tok/s
TTFT (avg)
0.62 s
VRAM (avg)
22.8 GB
MTP acceptance rate
—
TTFB
0.72 GB
Power draw
272.5 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-27B
Quantization
IQ1_S
Framework
Ollama
Version
v0.49
Context length
32768 tokens
Batch size
512
GPU layers
28
Flash Attention
Off

Hardware

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

GPU
NVIDIA RTX 3090
Nominal VRAM
24 GB
Measured VRAM (avg)
22.8 GB
OS
Ubuntu 22.04
Driver
570.86
CUDA
12.6
Power draw
272.5 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

    v0.49 · Ubuntu 22.04 · CUDA 12.6 · 32768 ctx

    89.8 tok/s

    Decode

    459.43 tok/s

    Prefill

    0.62 s

    TTFT

    22.8 GB

    VRAM

    —

    MTP

    272.5 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=2 running model_id=50 at IQ1_S