Back to search results
Qwen3-1.7B · Q3_K_M
AMD Radeon RX 7900 XTX24GBOllama v0.38L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-1.7B (Q3_K_M) on AMD Radeon RX 7900 XTX with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
196.24 tok/s
Decode
Decode speed
705.31 tok/s
Prefill
Prefill speed
0.21 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 · IQ3_XS Decode 234.47 · Prefill 1079.52 ·
- llama.cpp · Q4_K_M Decode 178.72 · Prefill 842.7 ·
- Ollama · Q3_K_M (current)Decode 196.24 · Prefill 705.31 ·
- Ollama · Q8_0 Decode 111.35 · Prefill 362.65 ·
- Strata · Q4_K_S Decode 249 · Prefill 1211.72 ·
Core figures
- Decode (avg)
- 196.24 tok/s
- Prefill (avg)
- 705.31 tok/s
- TTFT (avg)
- 0.21 s
- VRAM (avg)
- 4.53 GB
- MTP acceptance rate
- —
- TTFB
- 1.57 GB
- Power draw
- 328 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-1.7B
- Quantization
- Q3_K_M
- Framework
- Ollama
- Version
- v0.38
- Context length
- 32768 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
- AMD Radeon RX 7900 XTX
- Nominal VRAM
- 24 GB
- Measured VRAM (avg)
- 4.53 GB
- OS
- Ubuntu 22.04
- Driver
- 570.86
- CUDA
- 12.4
- Power draw
- 328 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.38 · Ubuntu 22.04 · CUDA 12.4 · 32768 ctx
196.24 tok/s
Decode
705.31 tok/s
Prefill
0.21 s
TTFT
4.53 GB
VRAM
—
MTP
328 W
Power draw
L2 batch seed 2026-10-10: Ollama on hw_id=11 running model_id=55 at Q3_K_M