Model benchmarks
Qwen3.8-9B-Q8_0:latest local LLM performance
As of August 2026, Qwen3.8-9B-Q8_0:latest runs at up to 76.5 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
OllamaQ8_0
Model size
9.2B
Peak speed
76.5 tok/s
Average speed
75.0 tok/s
Min memory
10.2 GB
Max context
7,505 tokens
Best quality
91.6
Benchmark runs
2
GPUs tested
1
Performance by hardware and tool
Every hardware/tool/quantization combination Qwen3.8-9B-Q8_0:latest has been benchmarked on, ranked by peak token generation speed. Last updated August 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| AMD Radeon RX 7900 XTX | Ollama | Q8_0 | 76.5 tok/s | 75.0 tok/s | 10.2 GB | 7,505 tokens | 72.8 | 2 |
Frequently asked questions
- How fast is Qwen3.8-9B-Q8_0:latest for local inference?
- Across 2 community benchmark runs, Qwen3.8-9B-Q8_0:latest reaches up to 76.5 tok/s and averages 75.0 tok/s, with the fastest results on AMD Radeon RX 7900 XTX.
- How much memory does Qwen3.8-9B-Q8_0:latest need?
- The leanest observed configuration used about 10.2 GB of memory (quantizations tested: Q8_0).
- Which tools have been used to run Qwen3.8-9B-Q8_0:latest?
- Benchmarks were submitted using Ollama. Results are community-contributed and updated as new runs arrive.