Arao AI
Back to search results

Qwen3.5-0.8B · Q5_K_M

Start a discussion
NVIDIA RTX 3060 12GB12GBOllama v0.25L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-0.8B (Q5_K_M) on NVIDIA RTX 3060 12GB with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

118.62 tok/s

Decode

Decode speed

422.11 tok/s

Prefill

Prefill speed

1.09 s

TTFT

Time to first token

3.66 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. llama.cpp · Q3_K_S Decode 187.82 · Prefill 792.93 ·
  2. llama.cpp · Q5_K_S Decode 142.06 · Prefill 686.26 ·
  3. Ollama · Q3_K_L Decode 167.74 · Prefill 790.34 ·
  4. Ollama · Q5_K_M (current)Decode 118.62 · Prefill 422.11 ·
  5. Strata · Q3_K_M Decode 279.25 · Prefill 1294.74 ·
  6. Strata · Q5_K_S Decode 214.78 · Prefill 1075.84 ·
  7. llama.cpp · Q8_0 Decode 312 · Prefill 2340 ·

Core figures

Decode (avg)
118.62 tok/s
Prefill (avg)
422.11 tok/s
TTFT (avg)
1.09 s
VRAM (avg)
3.66 GB
MTP acceptance rate
—
TTFB
0.95 GB
Power draw
158.8 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
Q5_K_M
Framework
Ollama
Version
v0.25
Context length
16384 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 3060 12GB
Nominal VRAM
12 GB
Measured VRAM (avg)
3.66 GB
OS
macOS 15.0
Driver
560.94
CUDA
12.8
Power draw
158.8 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

    v0.25 · macOS 15.0 · CUDA 12.8 · 16384 ctx

    118.62 tok/s

    Decode

    422.11 tok/s

    Prefill

    1.09 s

    TTFT

    3.66 GB

    VRAM

    —

    MTP

    158.8 W

    Power draw

    L2 batch seed 2026-10-10: Ollama on hw_id=15 running model_id=51 at Q5_K_M