Arao AI
Back to search results

Qwen3.5-0.8B · Q3_K_S

Start a discussion
NVIDIA RTX 507012GBOllama v0.23L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-0.8B (Q3_K_S) on NVIDIA RTX 5070 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

197.53 tok/s

Decode

Decode speed

685.98 tok/s

Prefill

Prefill speed

1.82 s

TTFT

Time to first token

3.19 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. vLLM · IQ3_XS Decode 223.3 · Prefill 1047.53 ·
  2. vLLM · IQ4_XS Decode 188.25 · Prefill 873.82 ·
  3. Ollama · Q3_K_S (current)Decode 197.53 · Prefill 685.98 ·
  4. Ollama · Q5_K_S Decode 124.72 · Prefill 677.51 ·
  5. Strata · IQ4_XS Decode 233.02 · Prefill 915.89 ·
  6. Strata · Q6_K Decode 189.01 · Prefill 746.35 ·
  7. llama.cpp · Q8_0 Decode 582.4 · Prefill 4368 ·

Core figures

Decode (avg)
197.53 tok/s
Prefill (avg)
685.98 tok/s
TTFT (avg)
1.82 s
VRAM (avg)
3.19 GB
MTP acceptance rate
—
TTFB
1.58 GB
Power draw
174.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
Q3_K_S
Framework
Ollama
Version
v0.23
Context length
8192 tokens
Batch size
256
GPU layers
99
Flash Attention
On

Hardware

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

GPU
NVIDIA RTX 5070
Nominal VRAM
12 GB
Measured VRAM (avg)
3.19 GB
OS
Windows 11 23H2
Driver
570.86
CUDA
12.8
Power draw
174.2 W

Sources & evidence

1 measured records in total, each traceable to its original source

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-10

    v0.23 · Windows 11 23H2 · CUDA 12.8 · 8192 ctx

    197.53 tok/s

    Decode

    685.98 tok/s

    Prefill

    1.82 s

    TTFT

    3.19 GB

    VRAM

    —

    MTP

    174.2 W

    Power draw

    L2 batch seed 2026-10-10: Ollama on hw_id=18 running model_id=51 at Q3_K_S