Arao AI
Back to search results

Qwen3.5-4B · Q2_K

Start a discussion
NVIDIA RTX 4080 Super16GBOllama v0.26L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-4B (Q2_K) on NVIDIA RTX 4080 Super with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

231.86 tok/s

Decode

Decode speed

790.98 tok/s

Prefill

Prefill speed

1.68 s

TTFT

Time to first token

6.72 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

16 days ago

Last verified

Performance

  1. vLLM · Q4_K_S Decode 190.65 · Prefill 787.91 ·
  2. Ollama · IQ2_M Decode 242.65 · Prefill 957.57 ·
  3. Ollama · Q2_K (current)Decode 231.86 · Prefill 790.98 ·
  4. vLLM · Q5_K_M Decode 152.06 · Prefill 772.68 ·
  5. Ollama · Q3_K_L Decode 202.33 · Prefill 955.67 ·

Core figures

Decode (avg)
231.86 tok/s
Prefill (avg)
790.98 tok/s
TTFT (avg)
1.68 s
VRAM (avg)
6.72 GB
MTP acceptance rate
—
TTFB
1.85 GB
Power draw
236.5 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-4B
Quantization
Q2_K
Framework
Ollama
Version
v0.26
Context length
4096 tokens
Batch size
256
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 4080 Super
Nominal VRAM
16 GB
Measured VRAM (avg)
6.72 GB
OS
Ubuntu 24.04
Driver
570.86
CUDA
12.6
Power draw
236.5 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

    v0.26 · Ubuntu 24.04 · CUDA 12.6 · 4096 ctx

    231.86 tok/s

    Decode

    790.98 tok/s

    Prefill

    1.68 s

    TTFT

    6.72 GB

    VRAM

    —

    MTP

    236.5 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=20 running model_id=48 at Q2_K