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

What AI models run on the RTX 5080?

The RTX 5080 has 16 GB of VRAM (960 GB/s). About 15.2 GB is usable for a model. 200 of 298 open models we track fit at 8K context.

200models fit (8K ctx)
189still fit at 32K ctx
37Blargest that fits
960 GB/smemory bandwidth

This card has 16 GB of VRAM. See every model that fits in 16 GB VRAM. Other 16 GB hardware: RTX 4060 Ti 16GB, RTX 4070 Ti Super, RTX 4080, RTX 4080 Super, RTX 5060 Ti 16GB, RTX 5070 Ti, RX 7800 XT, RX 7900 GRE.

Compare for local LLMs: RTX 5080 vs RTX 5070 TiRTX 5080 vs RTX 5090RTX 5080 vs RTX 4080 SuperRTX 5080 vs RTX 3090RTX 5080 vs RX 7900 XTX all comparisons

Using a specific tool? Ollama models that run on the RTX 5080 · LM Studio · llama.cpp offload

Models that fit, largest first

ModelParamsBest quant (8K)Needs32K contextMax tok/s (est.)Details
Maxwell V1 Flash37B (2.3B act.)Q2_K14.0 GBQ2_K1128details
Qwen3.6 35B A3B36B (3.0B act.)Q2_K13.6 GBQ2_K852details
Ornith 1.5 35B A3B36B (3.0B act.)Q2_K13.2 GBQ2_K879details
Qwen3.5 35B A3B36B (3.0B act.)Q2_K13.6 GBQ2_K852details
Sage A1.536B (4.7B act.)Q2_K13.4 GBQ2_K549details
Qwen AgentWorld 35B A3B35B (3.0B act.)Q2_K13.1 GBQ2_K853details
Yi 1.5 34B Chat34BQ2_K14.3 GBno75details
Nous Hermes 2 Yi 34B34BQ2_K14.8 GBno72details
DeepSeek R1 Distill Qwen 32B33BQ2_K14.2 GBno78details
Qwen3 32B33BQ2_K14.1 GBno78details
GLM Z1 32B 041433BQ2_K12.5 GBQ2_K79details
GLM 4 32B 041433BQ2_K12.6 GBQ2_K78details
Olmo 3 32B Think32BQ2_K13.0 GBQ2_K80details
Granite 4.0 H Small32B (8.8B act.)Q2_K11.7 GBQ2_K298details
Gemma 4 31B IT31BQ2_K14.7 GBno76details
Gemma 4 31B31BQ2_K13.9 GBno82details
GLM 4.7 Flash31B (4.6B act.)Q2_K11.4 GBQ2_K589details
Qwen3 Coder 30B A3B Instruct31B (3.0B act.)Q2_K12.1 GBQ2_K853details
North Mini Code 1.030B (3.3B act.)Q2_K11.7 GBQ2_K798details
Hy Memory 30B A3B30B (3.0B act.)Q2_K11.9 GBQ2_K853details
Muse Glimmer 30B30BQ2_K11.4 GBQ2_K86details
Granite 4.2 30B29BQ2_K12.7 GBno88details
Raon 1 Mini Preview29B (4.3B act.)Q2_K11.2 GBQ2_K593details
Qwen3.8 27B28BQ2_K11.5 GBQ2_K89details
Qwen3.6 27B28BQ2_K12.6 GBQ2_K80details
Qwen3.5 27B28BQ2_K12.6 GBQ2_K80details
Gemma 3 27B IT27BQ2_K11.7 GBQ2_K91details
Arete 27B27BQ3_K_M13.6 GBQ2_K73details
MiniMax H3 Image PE27BQ2_K11.3 GBQ2_K90details
Trinity Mini26B (2.0B act.)Q3_K_M12.3 GBQ3_K_M1055details
GLiDE 27B26BQ3_K_M13.2 GBQ2_K75details
DiffusionGemma 26B A4B IT26B (4.0B act.)Q3_K_M13.2 GBQ2_K491details
Gemma 4 26B A4B IT26B (4.0B act.)Q3_K_M13.5 GBQ2_K476details
LFM2.5 24B A2B24B (2.0B act.)Q3_K_M11.7 GBQ3_K_M982details
ERNIE 4.5 21B A3B PT22BQ4_K_M13.6 GBQ3_K_M71details
ERNIE 4.5 21B A3B Thinking22BQ4_K_M13.6 GBQ3_K_M71details
gpt-oss Safeguard 20B22B (4.8B act.)Q8_012.3 GBQ8_0356details
gpt-oss 20B21B (4.2B act.)Q8_012.3 GBQ8_0395details
Kimi VL A3B Thinking 250616B (3.0B act.)Q6_K13.5 GBQ5_K_M390details
Kimi VL A3B Thinking16B (3.0B act.)Q6_K13.5 GBQ5_K_M390details
Kimi VL A3B Instruct16B (3.0B act.)Q5_K_M12.2 GBQ5_K_M436details
DeepSeek MoE 16B Base16B (2.8B act.)Q4_K_M12.5 GBQ2_K512details
LLaDA2.1 Mini16B (1.4B act.)Q6_K13.4 GBQ5_K_M817details
Moonlight 16B A3B Instruct16B (3.0B act.)Q5_K_M12.2 GBQ5_K_M424details
DeepSeek Coder V2 Lite Instruct16B (2.7B act.)Q5_K_M11.9 GBQ5_K_M478details
DeepSeek V2 Lite16B (2.7B act.)Q6_K12.8 GBQ6_K440details
DeepSeek V2 Lite Chat16B (2.7B act.)Q5_K_M11.9 GBQ5_K_M478details
Qwen2.5 Coder 14B Instruct15BQ6_K13.5 GBQ3_K_M79details
DeepSeek R1 Distill Qwen 14B15BQ6_K13.5 GBQ3_K_M79details
Qwen3 14B15BQ6_K13.2 GBQ3_K_M79details
Phi 415BQ6_K13.4 GBQ2_K80details
Gemma 3 12B IT12BQ8_013.4 GBQ6_K77details
Llama Guard 4 12B12BQ6_K11.5 GBQ4_K_M98details
KORMo Web 11B11BQ8_013.0 GBQ5_K_M81details
Llama 3.2 11B Vision Instruct11BQ8_011.6 GBQ5_K_M92details
Llama 3.2 11B Vision11BQ8_012.4 GBQ5_K_M85details
GLM 4.6V Flash10BQ8_010.3 GBQ8_096details
GLM 4.1V 9B Thinking10BQ8_010.3 GBQ8_096details
Step3 VL 10B10BQ8_09.9 GBQ8_0110details
SenseNova Loop 9B Preview9.7BQ8_010.0 GBQ8_0101details
Qwen3.5 9B9.7BQ8_010.3 GBQ8_098details
Ornith 1.5 9B9.7BQ8_010.0 GBQ8_0101details
SenseNova Loop 9B9.4BQ8_010.0 GBQ8_0101details
MiMo V2.6 Distill Qwen 9B9.4BQ8_010.0 GBQ8_0101details
GLM 4 9B9.4BQ8_010.3 GBQ8_096details
Apertus v1.5 8B8.9BQ8_010.5 GBQ8_0101details
InternLM3 8B Instruct8.8BQ8_09.7 GBQ8_0103details
Granite 4.2 8B8.8BQ8_010.5 GBQ6_K103details
Granite 4.1 8B8.8BQ8_010.5 GBQ6_K103details
Granite 4.1 8B Llmon Preview8.8BQ8_010.5 GBQ6_K103details
Qwen3 VL 8B Instruct8.8BQ8_09.9 GBQ8_0110details
Molmo2 8B8.7BQ8_09.9 GBQ8_0110details
LFM2.5 8B A1B8.5B (1.0B act.)Q8_09.1 GBQ8_0902details
Qwen2.5 VL 7B Instruct8.3BQ8_08.7 GBQ8_0119details
UI TARS 1.5 7B8.3BQ8_08.7 GBQ8_0119details
olmOCR 2 7B 10258.3BQ8_08.7 GBQ8_0119details
olmOCR 7B 0225 Preview8.3BQ8_08.7 GBQ8_0119details
UI TARS 7B DPO8.3BQ8_08.7 GBQ8_0119details
Qwen3 8B8.2BQ8_09.9 GBQ8_0110details
DeepSeek R1 0528 Qwen3 8B8.2BQ8_09.9 GBQ8_0110details
Granite 3.3 8B Instruct8.2BQ8_09.8 GBQ8_0111details
Granite 3.1 8B Instruct8.2BQ8_09.8 GBQ8_0111details
Granite 3.2 8B Instruct8.2BQ8_09.8 GBQ8_0111details
Apertus 8B Instruct 25098.1BQ8_09.6 GBQ8_0112details
Llama 3.1 8B Instruct8.0BQ8_09.6 GBQ8_0112details
Llama 3.1 8B8.0BQ8_09.6 GBQ8_0112details
Hermes 3 Llama 3.1 8B8.0BQ8_09.6 GBQ8_0112details
Llama Guard 3 8B8.0BQ8_09.6 GBQ8_0112details
DeepSeek R1 Distill Llama 8B8.0BQ8_09.6 GBQ8_0112details
Meta Llama 3 8B Instruct8.0BQ8_09.6 GBQ8_0112details
Meta Llama Guard 2 8B8.0BQ8_09.6 GBQ8_0112details
Meta Llama 3.1 8B Instruct8.0BQ8_09.6 GBQ8_0112details
Aya Expanse 8B8.0BQ8_09.8 GBQ8_0112details
Ling 3.0 Tiny7.9B (1.4B act.)Q8_08.7 GBQ8_0652details
MiMo 7B RL7.8BQ8_09.4 GBQ8_0118details
InternLM2.5 7B Chat7.7BQ8_09.2 GBQ8_0117details
InternLM2 Chat 7B7.7BQ8_09.2 GBQ8_0117details
Qwen2.5 7B Instruct7.6BQ8_08.7 GBQ8_0119details
DeepSeek R1 Distill Qwen 7B7.6BQ8_08.7 GBQ8_0119details
Qwen2.5 Coder 7B Instruct7.6BQ8_08.7 GBQ8_0119details
Olmo 3 7B Instruct7.3BQ8_010.3 GBQ8_0124details
Olmo 3 1025 7B7.3BQ8_010.3 GBQ8_0124details
Olmo 3 7B Think7.3BQ8_010.3 GBQ8_0124details
Mistral 7B v0.17.2BQ8_08.6 GBQ8_0125details
Mistral 7B Instruct v0.27.2BQ8_08.6 GBQ8_0125details
Mistral 7B Instruct v0.17.2BQ8_08.6 GBQ8_0125details
Falcon 7B7.2BQ8_07.7 GBQ8_0125details
Falcon 7B Instruct7.2BQ8_07.4 GBQ8_0130details
Granite 4.0 H Tiny6.9B (1.5B act.)F1613.6 GBQ8_0327details
OLMoE 1B 7B 09246.9B (1.3B act.)Q8_08.4 GBQ8_0704details
DeepSeek Coder 7B Instruct v1.56.9BQ8_011.2 GBno131details
DeepSeek Coder 6.7B Instruct6.7BQ8_011.1 GBno134details
DeepSeek Coder 6.7B Base6.7BQ8_011.1 GBno134details
Llama 2 7B HF6.7BQ8_011.1 GBno134details
Yi 6B 200K6.1BF1612.3 GBQ8_079details
Yi 6B6.1BF1612.3 GBQ8_079details
Molmo2 4B4.9BF1610.0 GBF16109details
WeVisOne VL 4B4.8BF1610.0 GBF16109details
Mage VL Cowork4.7BF1610.0 GBF16109details
Qianfan OCR4.7BF1610.1 GBF16109details
Qwen3.5 4B4.7BF169.2 GBF16111details
SingVL S1 4B4.5BF169.0 GBF16114details
LightOnOCR 3 4B4.5BF169.0 GBF16114details
Intern Decision 4B4.5BF169.0 GBF16114details
Qwen3 VL 4B Instruct4.4BF169.3 GBF16119details
Gemma 3 4B IT4.3BF168.4 GBF16124details
MedGemma 1.5 4B IT4.3BF168.4 GBF16124details
MedGemma 4B IT4.3BF168.4 GBF16124details
TranslateGemma 4B IT4.3BF169.2 GBF16112details
Gemma 3 4B PT4.3BF168.4 GBF16124details
Phi 3.5 Vision Instruct4.1BF1611.2 GBQ4_K_M116details
Qwen3 4B4.0BF169.3 GBF16119details
Qwen3 4B Instruct 25074.0BF169.3 GBF16119details
Granite Vision 4.1 4B4.0BF167.6 GBF16141details
Phi 4 Mini Instruct3.8BF168.9 GBF16125details
Phi 3 Mini 4K Instruct3.8BF1610.6 GBQ5_K_M126details
Phi 3.5 Mini Instruct3.8BF1610.6 GBQ5_K_M126details
Phi 3 Mini 128K Instruct3.8BF1610.6 GBQ5_K_M126details
Qwen2.5 VL 3B Instruct3.8BF168.0 GBF16128details
Granite 4.2 3B3.7BF168.0 GBF16131details
Granite 4.1 3B Llmon Preview3.7BF168.0 GBF16131details
Raon 1 Nano3.5BF167.0 GBF16153details
Granite 4.1 3B3.4BF167.6 GBF16141details
Granite 4.0 Micro3.4BF167.6 GBF16141details
DeepSeek OCR 23.4B (1.2B act.)F166.6 GBF16464details
DeepSeek VL2 Tiny3.4B (1.2B act.)F167.4 GBF16408details
Tiny Aya Global3.3BF167.5 GBF16143details
Unlimited OCR 23.3B (1.1B act.)F166.6 GBF16475details
Unlimited OCR3.3B (1.1B act.)F166.6 GBF16478details
DeepSeek OCR3.3B (1.1B act.)F166.6 GBF16478details
Granite 3.1 3B A800M Instruct3.3B (883M act.)F167.1 GBF16543details
Llama 3.2 3B Instruct3.2BF167.5 GBF16149details
Llama 3.2 3B3.2BF167.5 GBF16149details
Hermes 3 Llama 3.2 3B3.2BF167.5 GBF16149details
d1 3B3.1BF165.8 GBF16178details
LFM2.5 VL 3B3.1BF165.8 GBF16178details
Qwen2.5 3B Instruct3.1BF166.7 GBF16156details
SmolLM3 3B3.1BF166.9 GBF16156details
SmolLM3 3B Base3.1BF166.9 GBF16156details
Phi 22.8BF168.2 GBQ8_0173details
LFM2.5 2.6B2.7BF1610.8 GBF1689details
Granite 3.3 2B Instruct2.5BF165.8 GBF16189details
MiniCPM5 2B2.5BF165.7 GBF16191details
WeVisOne VL 2B2.4BF165.4 GBF16236details
Cosmos Reason2 2B2.4BF165.4 GBF16236details
Qwen3.5 2B2.3BF164.6 GBF16246details
SmolVLM Instruct2.2BF165.4 GBF16265details
Qwen3 1.7B2.0BF165.4 GBF16236details
d1 2B1.9BF164.0 GBF16277details
LFM3 VL 2B1.9BF164.0 GBF16277details
DeepSeek R1 Distill Qwen 1.5B1.8BF164.2 GBF16270details
LFM3 1.7B1.7BF167.2 GBF16138details
LFM3 1.7B Base1.7BF164.0 GBF16277details
SmolLM2 1.7B Instruct1.7BF165.2 GBF16280details
SmolLM2 1.7B1.7BF165.2 GBF16280details
SmolLM 1.7B1.7BF165.2 GBF16280details
Granite 4.0 1B1.6BF164.3 GBF16294details
Qwen2.5 1.5B Instruct1.5BF163.8 GBF16311details
OLMo 2 0425 1B1.5BF164.4 GBF16323details
DeepSeek Coder 1.3B Instruct1.3BF164.5 GBF16356details
Llama 3.2 1B1.2BF163.2 GBF16387details
Llama 3.2 1B Instruct1.2BF163.2 GBF16387details
LFM2.5 1.2B Instruct1.2BF165.0 GBF16205details
LFM2 1.2B1.2BF163.0 GBF16410details
HunyuanOCR1.1BF163.5 GBF16429details
PaddleOCR VL 1.6959MF162.5 GBF16501details
Qwen3.5 0.8B873MF162.4 GBF16616details
LightOnOCR 3 0.8B853MF162.4 GBF16633details
FastVLM 0.5B759MF162.2 GBF16633details
Qwen3 0.6B752MF163.0 GBF16636details
GOT OCR2.0716MF162.8 GBF16670details
Nemotron 3.5 Parse631MF161.9 GBF16735details
GOT OCR 2.0 HF561MF162.5 GBF16856details
SmolVLM2 500M Video Instruct507MF161.6 GBF161170details
SmolVLM 500M Instruct507MF161.6 GBF161170details
Qwen2.5 0.5B Instruct494MF161.7 GBF16972details
LFM2.5 VL 450M449MF161.3 GBF161349details
SmolLM2 360M Instruct362MF161.5 GBF161323details
SmolLM2 360M362MF161.5 GBF161323details
LFM2.5 350M354MF161.9 GBF16675details

Bigger models with CPU offload

These popular models don't fit in the RTX 5080's VRAM at 4-bit, but run with llama.cpp offload, keeping part of the model in system RAM. Speed range is DDR4-3200 to DDR5-6000 (estimate). Method.

ModelParamsOffload plan
GLM 5.3 Flash321B MoEOffload Q2_K, 128 GB RAM · ~7.5–15 tok/s
gpt-oss 120B117B MoEOffload Q4_K_M, 64 GB RAM · ~14–29 tok/s
DeepSeek V4 Flash 0731304B MoEOffload Q2_K, 128 GB RAM · ~8.5–16 tok/s
DeepSeek V4 Flash291B MoEOffload Q3_K_M, 128 GB RAM · ~7.3–15 tok/s
GLM 4.5 Air110B MoEOffload Q4_K_M, 64 GB RAM · ~5.8–11 tok/s
MiniMax M2.5229B MoEOffload Q4_K_M, 128 GB RAM · ~5.7–11 tok/s
Hy3299B MoEOffload Q3_K_M, 128 GB RAM · ~4.2–8.6 tok/s

Comparing cards? The RTX 5080 (launch MSRP $999) is in best GPUs for local LLMs under $1,000. See also Mac vs PC.

Just too big at 4-bit

These need up to 35% more memory than the RTX 5080 has at Q4_K_M and 8K context. A smaller quant or shorter context may work.

ModelQ4_K_M needsShort by
Trinity Mini15.8 GB0.6 GB
GLiDE 27B16.2 GB1.0 GB
MiniMax H3 Image PE16.8 GB1.6 GB
DiffusionGemma 26B A4B IT17.1 GB1.9 GB
Gemma 4 26B A4B IT17.3 GB2.1 GB
Gemma 3 27B IT17.3 GB2.1 GB
Arete 27B17.4 GB2.2 GB
Qwen3.8 27B17.6 GB2.4 GB
Muse Glimmer 30B17.9 GB2.7 GB
Qwen3.5 27B18.1 GB2.9 GB
Qwen3.6 27B18.1 GB2.9 GB
GLM 4.7 Flash18.3 GB3.1 GB
Hy Memory 30B A3B18.5 GB3.3 GB
Qwen3 Coder 30B A3B Instruct18.8 GB3.6 GB
North Mini Code 1.018.8 GB3.6 GB

Questions

What is the biggest model that runs on the RTX 5080?

Of the models we track, the largest that fits at 8K context is Maxwell V1 Flash (37B) at Q2_K, needing about 14.0 GB.

How much of the RTX 5080's memory can a model use?

About 15.2 GB: we assume 95% of the 16 GB is usable after driver and display overhead.

Spec source: NVIDIA specifications. Model data: Hugging Face Hub API. Speed is a bandwidth ceiling (bandwidth ÷ bytes read per token), not a benchmark. Methodology · Report an error.