2 builds of Qwen 3 1.7B measured on real machines — different packagers, precisions and engines, each a different file with its own numbers. The best each engine proved is first; every build has its own page with the machines and signatures behind it.
proved 64K context proved by qwen
proved by at least one build: Tool calling · Faithful to tool results · Chained tool calls · Structured output · Sustained output · Extended thinking · Reasons about code · Synthesises sources
| build | publisher | precision | engine | whose work | context proved | best tok/s | machines |
|---|---|---|---|---|---|---|---|
| Qwen/Qwen3-1.7B | qwen | — | vllm | — | 65,536 | — | 1 |
| hf.co/Qwen/Qwen3-1.7B-GGUF:Q8_0 | Qwen | Q8_0 | ollama | vendor | — | 5.9 | 1 |