Arao AI
Back to search results

Qwen3.5-0.8B · Q4_K_S

Start a discussion
NVIDIA RTX 508016GBOllama v0.45L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-0.8B (Q4_K_S) on NVIDIA RTX 5080 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

368.6 tok/s

Decode

Decode speed

1,525.44 tok/s

Prefill

Prefill speed

1.58 s

TTFT

Time to first token

3.41 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

17 days ago

Last verified

Performance

  1. vLLM · IQ3_S Decode 323.11 · Prefill 1397.43 ·
  2. Ollama · Q4_K_S (current)Decode 368.6 · Prefill 1525.44 ·
  3. Ollama · Q5_K_M Decode 319.12 · Prefill 1528.98 ·
  4. llama.cpp · IQ3_XS Decode 314.6 · Prefill 1036.31 ·
  5. llama.cpp · Q4_K_S Decode 332.25 · Prefill 1390.04 ·
  6. Strata · IQ2_M Decode 312.53 · Prefill 1045.98 ·
  7. Strata · IQ3_XS Decode 375.51 · Prefill 1862.92 ·
  8. llama.cpp · IQ2_M Decode 338.41 · Prefill 1613.66 ·
  9. Strata · FP16 Decode 178.36 · Prefill 737.11 ·
  10. Strata · Q4_K_S Decode 363.26 · Prefill 1495.67 ·

Core figures

Decode (avg)
368.6 tok/s
Prefill (avg)
1,525.44 tok/s
TTFT (avg)
1.58 s
VRAM (avg)
3.41 GB
MTP acceptance rate
—
TTFB
2.95 GB
Power draw
263.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
Q4_K_S
Framework
Ollama
Version
v0.45
Context length
4096 tokens
Batch size
512
GPU layers
33
Flash Attention
Off

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)
3.41 GB
OS
Windows 11 23H2
Driver
570.86
CUDA
12.4
Power draw
263.9 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

    v0.45 · Windows 11 23H2 · CUDA 12.4 · 4096 ctx

    368.6 tok/s

    Decode

    1,525.44 tok/s

    Prefill

    1.58 s

    TTFT

    3.41 GB

    VRAM

    —

    MTP

    263.9 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=14 running model_id=51 at Q4_K_S