Best local LLM for rtx 5080
Top 7 open-source picks for rtx 5080, ranked by benchmark performance and real-world fit. Updated monthly.
Qwen 3 14B
A 14B dense model from Alibaba that matches Qwen 2.5 32B Base on STEM and code, with the same hybrid thinking system as the rest of the Qwen 3 family. The pragmatic sweet spot for a single 24GB GPU.
Phi-4 Reasoning 14B
Microsoft's 14B reasoner that beats R1-Distill-Llama-70B on AIME and GPQA with 50x fewer parameters. MIT-licensed, English-first, with a 32K context.
DeepSeek R1 Distill Qwen 14B
DeepSeek's R1 reasoning distilled into Qwen 14B under MIT. AIME24 69.7 and MATH-500 93.9 — beats o1-mini on most reasoning benchmarks.
Phi-4 14B
Microsoft's Phi-4 14B, trained on ultra-curated synthetic data with a heavy STEM bias. The 14B reasoning leader at the end of 2024.
Qwen 2.5 14B Instruct
Alibaba's Apache 2.0 dense 14B hitting MMLU 79.7 and HumanEval 83.5 across 29+ languages. The pragmatic sweet spot for self-hosted general-purpose chat.
Qwen 2.5 Coder 14B Instruct
Alibaba's Qwen 2.5 Coder 14B under Apache 2.0 with HumanEval 89.6 and LiveCodeBench 37.1. The VRAM sweet spot for serious self-hosted code generation.
gpt-oss 20B
OpenAI's compact open-weight MoE with 3.6B active out of 21B total parameters. Matches o3-mini on a laptop-class GPU under Apache 2.0.