Qwen3-0.6B
14 records across 5 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| RTX 3070 | Qwen3-0.6B | unspecified | vllm | 1676 | – | – | – | 512 | 2026-09-30 | community | – | source |
| RTX 3070 | Qwen3-0.6B | unspecified | vllm | 1671 | – | – | – | 512 | 2026-09-30 | community | – | source |
| B70 Arc Pro | Qwen3-0.6B | Q4_K_M | Vulkan | 475.76 | 20217.98 | – | – | 512 | 2026-10-02 | community | – | source |
| B70 Arc Pro | Qwen3-0.6B | Q4_K_M | Vulkan | 467.96 | 17508.58 | – | – | 512 | 2026-10-02 | community | – | source |
| B70 Arc Pro | Qwen3-0.6B | Q4_K_M | Vulkan | 456.94 | 25346.93 | – | – | 512 | 2026-10-02 | community | – | source |
| B70 Arc Pro | Qwen3-0.6B | Q4_K_M | Vulkan | 452.70 | 21235.41 | – | – | 512 | 2026-10-02 | community | – | source |
| RTX 4060 Ti | Qwen3-0.6B | Q4_K_M | Vulkan | 396.13 | 28280.84 | – | – | 1024 | 2026-10-02 | community | – | source |
| RTX 4060 Ti | Qwen3-0.6B | Q4_K_M | Vulkan | 390.33 | 24067.88 | – | – | 1024 | 2026-10-02 | community | – | source |
| RTX 4060 Ti | Qwen3-0.6B | Q4_K_M | Vulkan | 378.44 | 16094.75 | – | – | 1024 | 2026-10-02 | community | – | source |
| RTX 4060 Ti | Qwen3-0.6B | Q4_K_M | Vulkan | 376.92 | 17654.48 | – | – | 1024 | 2026-10-02 | community | – | source |
| M3 Ultra | Qwen3-0.6B | 8bit | oMLX | 118.6 | 4629.0 | – | – | 32768 | 2026-10-18 | community | – | source |
| M2 | Qwen3-0.6B | 8bit | oMLX | 86.8 | 1749.0 | – | – | 1024 | 2026-10-06 | community | – | source |
| M3 Ultra | Qwen3-0.6B | unknown | oMLX | 77.9 | 4278.0 | – | – | 32768 | 2026-10-08 | community | – | source |
| M2 | Qwen3-0.6B | 8bit | oMLX | 60.7 | 1317.0 | – | – | 4096 | 2026-10-06 | community | – | source |