Back to search results
Qwen2.5-0.5B-Instruct · IQ2_XS
NVIDIA RTX 308010GBllama.cpp v0.40L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen2.5-0.5B-Instruct (IQ2_XS) on NVIDIA RTX 3080 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
279.47 tok/s
Decode
Decode speed
1,475.5 tok/s
Prefill
Prefill speed
1.75 s
TTFT
Time to first token
2.6 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- llama.cpp · IQ2_XS (current)Decode 279.47 · Prefill 1475.5 ·
- Ollama · Q3_K_M Decode 199.79 · Prefill 1003.86 ·
- Ollama · Q4_K_M Decode 169.99 · Prefill 687.88 ·
Core figures
- Decode (avg)
- 279.47 tok/s
- Prefill (avg)
- 1,475.5 tok/s
- TTFT (avg)
- 1.75 s
- VRAM (avg)
- 2.6 GB
- MTP acceptance rate
- —
- TTFB
- 2.24 GB
- Power draw
- 286.8 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen2.5-0.5B-Instruct
- Quantization
- IQ2_XS
- Framework
- llama.cpp
- Version
- v0.40
- Context length
- 8192 tokens
- Batch size
- 256
- GPU layers
- 33
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 3080
- Nominal VRAM
- 10 GB
- Measured VRAM (avg)
- 2.6 GB
- OS
- Ubuntu 24.04
- Driver
- 555.85
- CUDA
- 12.4
- Power draw
- 286.8 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.40 · Ubuntu 24.04 · CUDA 12.4 · 8192 ctx
279.47 tok/s
Decode
1,475.5 tok/s
Prefill
1.75 s
TTFT
2.6 GB
VRAM
—
MTP
286.8 W
Power draw
L2 batch seed 2026-10-13: llama.cpp on hw_id=44 running model_id=59 at IQ2_XS