self-hosted/ai
§01·model · /models

Qwen3 14B

llmactiveApache-2.0

14B LLM by Alibaba (Qwen3) with hybrid thinking / non-thinking modes. Apache-2.0.

Download· 4 variants
§02·GPUs that run this model
20 total
GPUVRAMSeriesBest speedMin VRAMWorksBenchmarksRecipe
RTX 509032GB50123.8tokens/s3recipecheck ↗
RTX 508016GB5080.6tokens/s16GB2recipecheck ↗
RTX 3090 Ti24GB3076.2tokens/s24GB2recipecheck ↗
RTX 5070 Ti16GB5074.3tokens/s16GB2recipecheck ↗
RTX 309024GB3070tokens/s24GB2recipecheck ↗
RTX 3080 Ti12GB3069.9tokens/s2recipecheck ↗
RTX 4080 Super16GB4064.2tokens/s16GB2recipecheck ↗
RTX 408016GB4062tokens/s16GB2recipecheck ↗
RTX 4070 Ti Super16GB4058.1tokens/s16GB2recipecheck ↗
RTX 507012GB5054.2tokens/s12GB2recipecheck ↗
RTX 4070 Ti12GB4045.8tokens/s12GB2recipecheck ↗
RTX 4070 Super12GB4045.5tokens/s12GB2recipecheck ↗
RTX 5060 Ti16GB5041.1tokens/s16GB2recipecheck ↗
RTX 306012GB3031.2tokens/s2recipecheck ↗
RTX 4060 Ti 16GB16GB4027.4tokens/s16GB2recipecheck ↗
Apple M2 Pro16GBapple~0recipecheck ↗
RTX 407012GB40~0recipecheck ↗
RTX 409024GB40~0recipecheck ↗
RX 7800 XT16GBamd~0recipecheck ↗
RX 7900 XTX24GBamd~0recipecheck ↗

benchmarked·~ runs via recipe (not benchmarked)· untested·doesn't fit