Arao AI
Back to search results

Qwen3.5-4B · IQ2_M

Start a discussion
NVIDIA RTX 509032GBllama.cpp v0.33L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-4B (IQ2_M) on NVIDIA RTX 5090 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

354.14 tok/s

Decode

Decode speed

1,511.04 tok/s

Prefill

Prefill speed

1.52 s

TTFT

Time to first token

6.47 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

2 days ago

Last verified

Performance

  1. llama.cpp · Q3_K_M Decode 377.37 · Prefill 1718.05 ·
  2. llama.cpp · Q4_K_S Decode 334.66 · Prefill 1225.86 ·
  3. Strata · Q2_K Decode 338.27 · Prefill 1161 ·
  4. Strata · Q4_K_M Decode 318.56 · Prefill 1437.9 ·
  5. llama.cpp · IQ2_M (current)Decode 354.14 · Prefill 1511.04 ·
  6. Ollama · IQ2_M Decode 347.38 · Prefill 1126.85 ·
  7. Ollama · IQ2_XS Decode 333.52 · Prefill 1258.8 ·
  8. llama.cpp · Q3_K_L Decode 338.21 · Prefill 1409.78 ·
  9. vLLM · Q3_K_M Decode 356.1 · Prefill 1633.97 ·
  10. vLLM · Q3_K_S Decode 324.89 · Prefill 1253.12 ·
  11. Strata · Q4_K_S Decode 353.67 · Prefill 1676.75 ·

Core figures

Decode (avg)
354.14 tok/s
Prefill (avg)
1,511.04 tok/s
TTFT (avg)
1.52 s
VRAM (avg)
6.47 GB
MTP acceptance rate
—
TTFB
2.83 GB
Power draw
256.4 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-4B
Quantization
IQ2_M
Framework
llama.cpp
Version
v0.33
Context length
2048 tokens
Batch size
256
GPU layers
20
Flash Attention
On

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)
6.47 GB
OS
Ubuntu 24.04
Driver
560.94
CUDA
12.8
Power draw
256.4 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-16

    v0.33 · Ubuntu 24.04 · CUDA 12.8 · 2048 ctx

    354.14 tok/s

    Decode

    1,511.04 tok/s

    Prefill

    1.52 s

    TTFT

    6.47 GB

    VRAM

    —

    MTP

    256.4 W

    Power draw

    L2 batch seed 2026-10-16: llama.cpp on hw_id=13 running model_id=48 at IQ2_M