RunsOnMy ModelsGPUs & MacsBy VRAMBest GPUCan I run…?OllamaStart hereAPI pricesVRAM calculatorNew

RTX 5080 vs RTX 5090 for local LLMs

For local LLMs the RTX 5090 is the stronger pick: it runs 43 of the top 60 vs 32, and it has the higher speed ceiling. It launched at $1,000 more.

Specs that matter for LLMs

RTX 5080RTX 5090
Memory (VRAM)16 GB32 GB
Usable for a model (our estimate)15.2 GB30.4 GB
Memory bandwidth960 GB/s1792 GB/s
Launch MSRP$999$1,999
Launch $ per GB of memory$62$62
Top 60 models that fit (4-bit or better, 8K ctx)3243
…of those at 8-bit or better3034
Largest top-60 model that fitsgpt-oss 20BQwen3.5 35B A3B
Offload headroom: more top-60 models via llama.cpp CPU offload (≥3 tok/s est., up to 128 GB RAM)18 more (1 more below 3 tok/s)7 more (1 more below 3 tok/s)

Top 60 = the 60 most-downloaded open models we track. Launch MSRP from vendor announcements. How we calculate.

Estimated speed on popular models

Best quant that fits at 8K context, with a tokens/sec ceiling from memory bandwidth (real speed is typically 50–80% of it). "Offload" means part of the model sits in system RAM. Estimates, not benchmarks.

ModelNeeds at 4-bitRTX 5080RTX 5090
Qwen3 8B6.5 GBQ8_0 · ~110 tok/sF16 · ~109 tok/s
Llama 3.1 8B Instruct6.2 GBQ8_0 · ~112 tok/sF16 · ~112 tok/s
Qwen3 14B10.3 GBQ6_K · ~79 tok/sQ8_0 · ~114 tok/s
gpt-oss 20B11.8 GBQ8_0 · ~395 tok/sF16 · ~648 tok/s
Gemma 3 27B IT17.3 GBOffload Q4_K_M, 32 GB RAM · ~7.3–13 tok/sQ6_K · ~81 tok/s
Qwen3 32B21.1 GBOffload Q4_K_M, 32 GB RAM · ~3.3–6.5 tok/sQ5_K_M · ~77 tok/s
Qwen3 Coder 30B A3B Instruct18.8 GBOffload Q4_K_M, 32 GB RAM · ~68–119 tok/sQ6_K · ~726 tok/s
Llama 3.3 70B Instruct42.7 GBOffload Q4_K_M, 64 GB RAM · ~0.8–1.6 tok/sOffload Q4_K_M, 32 GB RAM · ~1.7–3.3 tok/s
gpt-oss 120B59.6 GBOffload Q4_K_M, 64 GB RAM · ~14–29 tok/sOffload Q4_K_M, 64 GB RAM · ~22–44 tok/s

Models only one of them runs

Only the RTX 5080

None.

Only the RTX 5090

More comparisons

RTX 5070 Ti vs RTX 5080RTX 4080 Super vs RTX 5080RTX 3090 vs RTX 5080RTX 5080 vs RX 7900 XTXRTX 4090 vs RTX 5090RTX 3090 vs RTX 5090Mac M4 Max 128GB vs RTX 5090DGX Spark vs RTX 5090 All GPU comparisons

See every model on the RTX 5080 or the RTX 5090, or try your own settings in the VRAM calculator.