Back to search results
Qwen3-1.7B · Q3_K_M
NVIDIA RTX 508016GBOllama v0.47L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-1.7B (Q3_K_M) on NVIDIA RTX 5080 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
198.41 tok/s
Decode
Decode speed
879.72 tok/s
Prefill
Prefill speed
2.37 s
TTFT
Time to first token
4.53 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- llama.cpp · Q4_K_S Decode 194.19 · Prefill 976.97 ·
- llama.cpp · Q8_0 Decode 121.42 · Prefill 409.38 ·
- Ollama · Q3_K_M (current)Decode 198.41 · Prefill 879.72 ·
- Ollama · Q8_0 Decode 116.38 · Prefill 555.86 ·
Core figures
- Decode (avg)
- 198.41 tok/s
- Prefill (avg)
- 879.72 tok/s
- TTFT (avg)
- 2.37 s
- VRAM (avg)
- 4.53 GB
- MTP acceptance rate
- —
- TTFB
- 1.59 GB
- Power draw
- 339.2 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-1.7B
- Quantization
- Q3_K_M
- Framework
- Ollama
- Version
- v0.47
- Context length
- 2048 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 5080
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 4.53 GB
- OS
- Ubuntu 22.04
- Driver
- 570.86
- CUDA
- 12.8
- Power draw
- 339.2 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.47 · Ubuntu 22.04 · CUDA 12.8 · 2048 ctx
198.41 tok/s
Decode
879.72 tok/s
Prefill
2.37 s
TTFT
4.53 GB
VRAM
—
MTP
339.2 W
Power draw
L2 batch seed 2026-10-10: Ollama on hw_id=14 running model_id=55 at Q3_K_M