Arao AI
Back to search results

Qwen3.5-0.8B · Q5_K_S

Start a discussion
NVIDIA RTX 509032GBvLLM v0.22L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-0.8B (Q5_K_S) on NVIDIA RTX 5090 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

316.53 tok/s

Decode

Decode speed

1,148.64 tok/s

Prefill

Prefill speed

2.15 s

TTFT

Time to first token

3.61 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 · Q5_K_S (current)Decode 316.53 · Prefill 1148.64 ·
  2. Ollama · Q3_K_M Decode 315.13 · Prefill 1204.27 ·
  3. llama.cpp · Q2_K Decode 378.36 · Prefill 1748.97 ·
  4. vLLM · Q3_K_M Decode 330.24 · Prefill 1384.87 ·
  5. vLLM · Q4_K_S Decode 330.77 · Prefill 1336.98 ·
  6. llama.cpp · IQ2_M Decode 284.64 · Prefill 1115.95 ·
  7. llama.cpp · Q4_K_M Decode 351.6 · Prefill 1360.11 ·
  8. vLLM · Q6_K Decode 341.56 · Prefill 1623.94 ·
  9. Ollama · Q3_K_L Decode 320.91 · Prefill 1586.97 ·
  10. Ollama · Q8_0 Decode 384.44 · Prefill 1342.7 ·
  11. Strata · FP16 Decode 337.54 · Prefill 1202.28 ·
  12. Strata · Q6_K Decode 317.49 · Prefill 1303.51 ·

Core figures

Decode (avg)
316.53 tok/s
Prefill (avg)
1,148.64 tok/s
TTFT (avg)
2.15 s
VRAM (avg)
3.61 GB
MTP acceptance rate
—
TTFB
2.53 GB
Power draw
379 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
Q5_K_S
Framework
vLLM
Version
v0.22
Context length
16384 tokens
Batch size
8
GPU layers
999
Flash Attention
Off

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)
3.61 GB
OS
Windows 11 23H2
Driver
565.57
CUDA
12.8
Power draw
379 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

    v0.22 · Windows 11 23H2 · CUDA 12.8 · 16384 ctx

    316.53 tok/s

    Decode

    1,148.64 tok/s

    Prefill

    2.15 s

    TTFT

    3.61 GB

    VRAM

    —

    MTP

    379 W

    Power draw

    L2 batch seed 2026-10-19: vLLM on hw_id=13 running model_id=51 at Q5_K_S