RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

AI models that fit in 8 GB of VRAM

133 of 285 open models we track fit at 4-bit (Q4_K_M) with an 8K context on a 8 GB discrete GPU. About 7.6 GB is usable. 86 of those also fit at 8-bit. Typical 8 GB cards: RTX 4060 8GB, RTX 3070, Intel Arc A750.

133models fit at 4-bit, 8K
86also fit at 8-bit
11Blargest that fits
7.6 GBusable of 8 GB

GPUs and Macs with 8 GB

Cards and machines in our table with exactly 8 GB of memory. Macs use unified memory, so fewer models fit than on a 8 GB discrete GPU; open the Mac page for the default macOS limits.

RTX 3060 TiRTX 3070RTX 4060RTX 4060 Ti 8GBRTX 5060RX 7600

Models that fit, largest first

Memory needed at 8K context. "Tight" means the model uses 90–100% of usable VRAM. How we calculate.

ModelParamsQ4_K_M4-bit fitQ8_08-bit fit
Llama 3.2 11B Vision Instruct11B7.4 GBTight11.6 GBNo
GLM 4.6V Flash10B6.7 GBFits10.3 GBNo
GLM 4.1V 9B Thinking10B6.7 GBFits10.3 GBNo
Step3 VL 10B10B6.5 GBFits9.9 GBNo
SenseNova Loop 9B Preview9.7B6.4 GBFits10.0 GBNo
Qwen3.5 9B9.7B6.4 GBFits10.0 GBNo
Ornith 1.5 9B9.7B6.6 GBFits10.0 GBNo
Qwen3.5 9B Base9.7B6.4 GBFits10.0 GBNo
MiMo V2.6 Distill Qwen 9B9.4B6.6 GBFits10.0 GBNo
internlm3 8b instruct8.8B6.0 GBFits9.7 GBNo
granite 4.2 8b8.8B6.8 GBFits10.5 GBNo
granite 4.1 8b8.8B6.8 GBFits10.5 GBNo
Qwen3 VL 8B Instruct8.8B6.5 GBFits9.9 GBNo
Molmo2 8B8.7B6.5 GBFits9.9 GBNo
LFM2.5 8B A1B8.5B MoE5.5 GBFits9.1 GBNo
Qwen2.5 VL 7B Instruct8.3B5.5 GBFits8.7 GBNo
UI TARS 1.5 7B8.3B5.5 GBFits8.7 GBNo
olmOCR 2 7B 10258.3B5.5 GBFits8.7 GBNo
olmOCR 7B 0225 preview8.3B5.5 GBFits8.7 GBNo
UI TARS 7B DPO8.3B5.5 GBFits8.7 GBNo
Qwen3 8B8.2B6.5 GBFits9.9 GBNo
DeepSeek R1 0528 Qwen3 8B8.2B6.5 GBFits9.9 GBNo
granite 3.3 8b instruct8.2B6.3 GBFits9.8 GBNo
granite 3.1 8b instruct8.2B6.3 GBFits9.8 GBNo
granite 3.2 8b instruct8.2B6.3 GBFits9.8 GBNo
Apertus 8B Instruct 25098.1B6.4 GBFits9.6 GBNo
Llama 3.1 8B Instruct8.0B6.2 GBFits9.6 GBNo
Llama 3.1 8B8.0B6.2 GBFits9.6 GBNo
Hermes 3 Llama 3.1 8B8.0B6.2 GBFits9.6 GBNo
DeepSeek R1 Distill Llama 8B8.0B6.2 GBFits9.6 GBNo
Meta Llama 3 8B Instruct8.0B6.2 GBFits9.6 GBNo
Meta Llama Guard 2 8B8.0B6.2 GBFits9.6 GBNo
Meta Llama 3.1 8B Instruct8.0B6.2 GBFits9.6 GBNo
Ling 3.0 tiny7.9B MoE5.5 GBFits8.7 GBNo
MiMo 7B RL7.8B6.2 GBFits9.4 GBNo
internlm2 5 7b chat7.7B6.0 GBFits9.2 GBNo
internlm2 chat 7b7.7B6.0 GBFits9.2 GBNo
Qwen2.5 7B Instruct7.6B5.5 GBFits8.7 GBNo
Qwen2.5 Coder 7B Instruct7.6B5.5 GBFits8.7 GBNo
DeepSeek R1 Distill Qwen 7B7.6B5.5 GBFits8.7 GBNo
Falcon H1R 7B7.6B5.3 GBFits8.5 GBNo
Olmo 3 7B Instruct7.3B7.3 GBTight10.3 GBNo
Olmo 3 1025 7B7.3B7.3 GBTight10.3 GBNo
Olmo 3 7B Think7.3B7.3 GBTight10.3 GBNo
Mistral 7B v0.17.2B5.5 GBFits8.6 GBNo
Mistral 7B Instruct v0.17.2B5.5 GBFits8.6 GBNo
granite 4.0 h tiny6.9B MoE4.6 GBFits7.5 GBTight
OLMoE 1B 7B 09246.9B MoE5.4 GBFits8.4 GBNo
Yi 6B 200K6.1B4.4 GBFits7.0 GBTight
Yi 6B6.1B4.4 GBFits7.0 GBTight
Molmo2 4B4.9B4.3 GBFits6.2 GBFits
WeVisOne VL 4B4.8B4.3 GBFits6.2 GBFits
Mage VL Cowork4.7B4.3 GBFits6.2 GBFits
Qianfan OCR4.7B4.4 GBFits6.2 GBFits
Qwen3.5 4B4.7B3.7 GBFits5.3 GBFits
S5 nano4.7B3.7 GBFits5.4 GBFits
LightOnOCR 3 4B4.5B3.6 GBFits5.3 GBFits
SingVL S1 4B4.5B3.6 GBFits5.3 GBFits
Intern Decision 4B4.5B3.6 GBFits5.3 GBFits
Qwen3 VL 4B Instruct4.4B4.1 GBFits5.8 GBFits
gemma 3 4b it4.3B3.5 GBFits5.0 GBFits
medgemma 1.5 4b it4.3B3.5 GBFits5.0 GBFits
medgemma 4b it4.3B3.5 GBFits5.0 GBFits
gemma 3 4b pt4.3B3.6 GBFits5.4 GBFits
Phi 3.5 vision instruct4.1B5.8 GBFits7.6 GBTight
Qwen3 4B4.0B4.1 GBFits5.8 GBFits
Qwen3 4B Instruct 25074.0B4.1 GBFits5.8 GBFits
granite vision 4.1 4b4.0B3.2 GBFits4.6 GBFits
Phi 4 mini instruct3.8B4.1 GBFits5.6 GBFits
Phi 3 mini 4k instruct3.8B5.7 GBFits7.2 GBTight
Phi 3.5 mini instruct3.8B5.7 GBFits7.2 GBTight
Phi 3 mini 128k instruct3.8B5.7 GBFits7.2 GBTight
Qwen2.5 VL 3B Instruct3.8B2.8 GBFits4.0 GBFits
granite 4.2 3b3.7B3.3 GBFits4.8 GBFits
granite 4.1 3b llmon preview3.7B3.3 GBFits4.8 GBFits
Raon 1 nano3.5B3.0 GBFits4.3 GBFits
granite 4.1 3b3.4B3.2 GBFits4.6 GBFits
granite 4.0 micro3.4B3.2 GBFits4.6 GBFits
DeepSeek OCR 23.4B MoE2.9 GBFits4.0 GBFits
deepseek vl2 tiny3.4B MoE3.0 GBFits4.5 GBFits
Unlimited OCR 23.3B MoE3.0 GBFits4.0 GBFits
Unlimited OCR3.3B MoE2.9 GBFits4.0 GBFits
DeepSeek OCR3.3B MoE2.9 GBFits4.0 GBFits
granite 3.1 3b a800m instruct3.3B MoE2.9 GBFits4.3 GBFits
Llama 3.2 3B Instruct3.2B3.4 GBFits4.7 GBFits
Llama 3.2 3B3.2B3.6 GBFits5.1 GBFits
Hermes 3 Llama 3.2 3B3.2B3.4 GBFits4.7 GBFits
d1 3B3.1B2.3 GBFits3.4 GBFits
LFM2.5 VL 3B3.1B2.3 GBFits3.4 GBFits
Qwen2.5 3B Instruct3.1B2.9 GBFits4.3 GBFits
SmolLM3 3B3.1B3.0 GBFits4.3 GBFits
SmolLM3 3B Base3.1B3.0 GBFits4.3 GBFits
phi 22.8B4.7 GBFits5.8 GBFits
LFM2.5 2.6B2.7B2.3 GBFits3.4 GBFits
granite 3.3 2b instruct2.5B2.6 GBFits3.6 GBFits
MiniCPM5 2B2.5B2.5 GBFits3.5 GBFits
WeVisOne VL 2B2.4B2.8 GBFits3.6 GBFits
Qwen3.5 2B2.3B2.2 GBFits2.8 GBFits
SmolVLM Instruct2.2B3.0 GBFits3.8 GBFits
Qwen3 1.7B2.0B2.6 GBFits3.3 GBFits
Qwen3.8 27B DSpine b162.0B2.2 GBFits3.1 GBFits
d1 2B1.9B1.8 GBFits2.5 GBFits
LFM3 VL 2B1.9B1.8 GBFits2.5 GBFits
DeepSeek R1 Distill Qwen 1.5B1.8B1.9 GBFits2.7 GBFits
LFM3 1.7B1.7B1.8 GBFits2.5 GBFits
LFM3 1.7B Base1.7B1.7 GBFits2.5 GBFits
SmolLM2 1.7B Instruct1.7B3.0 GBFits3.7 GBFits
SmolLM2 1.7B1.7B3.0 GBFits3.7 GBFits
SmolLM 1.7B1.7B3.0 GBFits3.7 GBFits
granite 4.0 1b1.6B2.2 GBFits2.8 GBFits
Qwen2.5 1.5B Instruct1.5B1.9 GBFits2.7 GBFits
OLMo 2 0425 1B1.5B2.5 GBFits3.1 GBFits
deepseek coder 1.3b instruct1.3B2.8 GBFits3.3 GBFits
Llama 3.2 1B1.2B1.8 GBFits2.4 GBFits
Llama 3.2 1B Instruct1.2B1.6 GBFits2.1 GBFits
LFM2.5 1.2B Instruct1.2B1.3 GBFits1.8 GBFits
HunyuanOCR1.1B2.0 GBFits2.5 GBFits
PaddleOCR VL 1.6959M1.3 GBFits1.7 GBFits
Qwen3.5 0.8B873M1.5 GBFits1.7 GBFits
LightOnOCR 3 0.8B853M1.5 GBFits1.7 GBFits
FastVLM 0.5B759M1.2 GBFits1.5 GBFits
Qwen3 0.6B752M1.9 GBFits2.2 GBFits
GOT OCR2 0716M1.8 GBFits2.1 GBFits
Nemotron 3.5 Parse631M1.1 GBFits1.5 GBFits
GOT OCR 2.0 hf561M1.8 GBFits2.0 GBFits
SmolVLM2 500M Video Instruct507M1.1 GBFits1.2 GBFits
SmolVLM 500M Instruct507M1.1 GBFits1.2 GBFits
Qwen2.5 0.5B Instruct494M1.2 GBFits1.4 GBFits
LFM2.5 VL 450M449M0.8 GBFits1.0 GBFits
SmolLM2 360M Instruct362M1.1 GBFits1.2 GBFits
SmolLM2 360M362M1.1 GBFits1.2 GBFits
LFM2.5 350M354M0.8 GBFits1.0 GBFits
LFM2 350M354M1.0 GBFits1.1 GBFits

Questions

How many AI models fit in 8 GB of VRAM?

133 of the 285 open models we track fit at 4-bit (Q4_K_M) with an 8K context. 86 also fit at 8-bit (Q8_0) at the same context.

What is the largest model that fits in 8 GB?

Of the models we track, the largest that fits at 4-bit with 8K context is Llama 3.2 11B Vision Instruct (11B), needing about 7.4 GB.

How much of 8 GB can a model actually use?

About 7.6 GB. We treat 95% of a discrete GPU's VRAM as usable after driver and display reserve, and a model "fits" when it needs at most 90% of that. The formulas are on the methodology page.

Other VRAM sizes

12 GB16 GB24 GB32 GB48 GB64 GB

A generic 8 GB discrete GPU is modelled with 95% of VRAM usable, the same rule as the rest of the site. For a specific card, including its bandwidth and estimated tokens/sec, open that GPU page. Data: Hugging Face Hub API and vendor spec pages. Report an error.