RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

AI models that fit in 24 GB of VRAM

195 of 285 open models we track fit at 4-bit (Q4_K_M) with an 8K context on a 24 GB discrete GPU. About 22.8 GB is usable. 161 of those also fit at 8-bit. Typical 24 GB cards: RTX 3090, RTX 4090, RTX 7900 XTX.

195models fit at 4-bit, 8K
161also fit at 8-bit
37Blargest that fits
22.8 GBusable of 24 GB

GPUs and Macs with 24 GB

Cards and machines in our table with exactly 24 GB of memory. Macs use unified memory, so fewer models fit than on a 24 GB discrete GPU; open the Mac page for the default macOS limits.

RTX 3090RTX 3090 TiRTX 4090RX 7900 XTXMac M2 24GB (Mac)Mac M3 24GB (Mac)Mac M4 Pro 24GB (Mac)

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
Maxwell V1 Flash37B MoE22.1 GBTight37.6 GBNo
Qwen3.6 35B A3B36B MoE22.1 GBTight36.2 GBNo
Ornith 1.5 35B A3B36B MoE21.4 GBTight36.2 GBNo
Qwen3.5 35B A3B36B MoE21.5 GBTight35.4 GBNo
Axion 1.0 35B35B MoE20.7 GBTight35.8 GBNo
Qwen AgentWorld 35B A3B35B MoE21.6 GBTight35.4 GBNo
Yi 34B 200K34B21.6 GBTight36.4 GBNo
Yi 34B34B21.6 GBTight36.4 GBNo
Yi 34B Chat34B21.6 GBTight36.4 GBNo
Yi 1.5 34B Chat34B21.6 GBTight36.4 GBNo
Nous Hermes 2 Yi 34B34B22.1 GBTight36.4 GBNo
DeepSeek R1 Distill Qwen 32B33B21.2 GBTight35.1 GBNo
Qwen3 32B33B21.1 GBTight35.1 GBNo
GLM Z1 32B 041433B19.5 GBFits33.4 GBNo
GLM 4 32B 041433B19.5 GBFits33.4 GBNo
granite 4.0 h small32B MoE18.9 GBFits32.6 GBNo
gemma 4 31B it31B20.0 GBFits33.3 GBNo
GLM 4.7 Flash31B MoE18.2 GBFits30.8 GBNo
Qwen3 Coder 30B A3B Instruct31B MoE18.7 GBFits31.7 GBNo
North Mini Code 1.030B MoE19.3 GBFits31.6 GBNo
Hy Memory 30B A3B30B MoE18.5 GBFits31.1 GBNo
Muse Glimmer 30B30B17.9 GBFits28.5 GBNo
granite 4.2 30b29B19.1 GBFits31.6 GBNo
Qwen3.8 27B28B16.8 GBFits28.4 GBNo
Qwen3.6 27B28B17.0 GBFits28.0 GBNo
Qwen3.5 27B28B17.0 GBFits28.0 GBNo
gemma 3 27b it27B17.3 GBFits28.7 GBNo
Arete 27B27B17.4 GBFits28.1 GBNo
MiniMax H3 Image PE27B16.8 GBFits28.0 GBNo
Trinity Mini26B MoE15.8 GBFits26.9 GBNo
GLiDE 27B26B16.2 GBFits27.2 GBNo
diffusiongemma 26B A4B it26B MoE17.1 GBFits26.4 GBNo
gemma 4 26B A4B it26B MoE17.2 GBFits26.4 GBNo
LFM2.5 24B A2B24B MoE14.3 GBFits24.5 GBNo
ERNIE 4.5 21B A3B PT22B13.5 GBFits22.6 GBTight
ERNIE 4.5 21B A3B Thinking22B13.5 GBFits22.6 GBTight
gpt oss safeguard 20b22B MoE11.8 GBFits12.3 GBFits
gpt oss 20b21B MoE11.8 GBFits12.3 GBFits
Groot 19B A3B 26102319B MoE12.7 GBFits19.9 GBFits
Kimi VL A3B Thinking 250616B MoE10.8 GBFits16.8 GBFits
Kimi VL A3B Instruct16B MoE10.8 GBFits16.8 GBFits
Kimi VL A3B Thinking16B MoE10.3 GBFits17.2 GBFits
deepseek moe 16b base16B MoE12.5 GBFits18.6 GBFits
LLaDA2.1 mini16B MoE10.3 GBFits17.1 GBFits
Moonlight 16B A3B Instruct16B MoE10.8 GBFits16.8 GBFits
DeepSeek Coder V2 Lite Instruct16B MoE10.5 GBFits16.4 GBFits
DeepSeek V2 Lite16B MoE9.8 GBFits16.4 GBFits
DeepSeek V2 Lite Chat16B MoE10.5 GBFits16.4 GBFits
Qwen2.5 Coder 14B Instruct15B10.6 GBFits16.8 GBFits
DeepSeek R1 Distill Qwen 14B15B10.6 GBFits16.8 GBFits
Qwen3 14B15B10.3 GBFits16.6 GBFits
phi 415B10.4 GBFits16.7 GBFits
gemma 3 12b it12B8.5 GBFits13.4 GBFits
Llama Guard 4 12B12B9.1 GBFits14.2 GBFits
Llama 3.2 11B Vision Instruct11B7.4 GBFits11.6 GBFits
Llama 3.2 11B Vision11B8.0 GBFits12.4 GBFits
GLM 4.6V Flash10B6.7 GBFits10.3 GBFits
GLM 4.1V 9B Thinking10B6.7 GBFits10.3 GBFits
Step3 VL 10B10B6.5 GBFits9.9 GBFits
SenseNova Loop 9B Preview9.7B6.4 GBFits10.0 GBFits
Qwen3.5 9B9.7B6.4 GBFits10.0 GBFits
Ornith 1.5 9B9.7B6.6 GBFits10.0 GBFits
Qwen3.5 9B Base9.7B6.4 GBFits10.0 GBFits
MiMo V2.6 Distill Qwen 9B9.4B6.6 GBFits10.0 GBFits
glm 4 9b9.4B11.5 GBFits15.0 GBFits
internlm3 8b instruct8.8B6.0 GBFits9.7 GBFits
granite 4.2 8b8.8B6.8 GBFits10.5 GBFits
granite 4.1 8b8.8B6.8 GBFits10.5 GBFits
Qwen3 VL 8B Instruct8.8B6.5 GBFits9.9 GBFits
Molmo2 8B8.7B6.5 GBFits9.9 GBFits
LFM2.5 8B A1B8.5B MoE5.5 GBFits9.1 GBFits
Qwen2.5 VL 7B Instruct8.3B5.5 GBFits8.7 GBFits
UI TARS 1.5 7B8.3B5.5 GBFits8.7 GBFits
olmOCR 2 7B 10258.3B5.5 GBFits8.7 GBFits
olmOCR 7B 0225 preview8.3B5.5 GBFits8.7 GBFits
UI TARS 7B DPO8.3B5.5 GBFits8.7 GBFits
Qwen3 8B8.2B6.5 GBFits9.9 GBFits
DeepSeek R1 0528 Qwen3 8B8.2B6.5 GBFits9.9 GBFits
granite 3.3 8b instruct8.2B6.3 GBFits9.8 GBFits
granite 3.1 8b instruct8.2B6.3 GBFits9.8 GBFits
granite 3.2 8b instruct8.2B6.3 GBFits9.8 GBFits
Apertus 8B Instruct 25098.1B6.4 GBFits9.6 GBFits
Llama 3.1 8B Instruct8.0B6.2 GBFits9.6 GBFits
Llama 3.1 8B8.0B6.2 GBFits9.6 GBFits
Hermes 3 Llama 3.1 8B8.0B6.2 GBFits9.6 GBFits
DeepSeek R1 Distill Llama 8B8.0B6.2 GBFits9.6 GBFits
Meta Llama 3 8B Instruct8.0B6.2 GBFits9.6 GBFits
Meta Llama Guard 2 8B8.0B6.2 GBFits9.6 GBFits
Meta Llama 3.1 8B Instruct8.0B6.2 GBFits9.6 GBFits
Ling 3.0 tiny7.9B MoE5.5 GBFits8.7 GBFits
MiMo 7B RL7.8B6.2 GBFits9.4 GBFits
internlm2 5 7b chat7.7B6.0 GBFits9.2 GBFits
internlm2 chat 7b7.7B6.0 GBFits9.2 GBFits
Qwen2.5 7B Instruct7.6B5.5 GBFits8.7 GBFits
Qwen2.5 Coder 7B Instruct7.6B5.5 GBFits8.7 GBFits
DeepSeek R1 Distill Qwen 7B7.6B5.5 GBFits8.7 GBFits
Falcon H1R 7B7.6B5.3 GBFits8.5 GBFits
Olmo 3 7B Instruct7.3B7.3 GBFits10.3 GBFits
Olmo 3 1025 7B7.3B7.3 GBFits10.3 GBFits
Olmo 3 7B Think7.3B7.3 GBFits10.3 GBFits
Mistral 7B v0.17.2B5.5 GBFits8.6 GBFits
Mistral 7B Instruct v0.17.2B5.5 GBFits8.6 GBFits
falcon 7b7.2B9.6 GBFits12.1 GBFits
falcon 7b instruct7.2B9.4 GBFits11.8 GBFits
granite 4.0 h tiny6.9B MoE4.6 GBFits7.5 GBFits
OLMoE 1B 7B 09246.9B MoE5.4 GBFits8.4 GBFits
deepseek coder 7b instruct v1.56.9B8.3 GBFits11.2 GBFits
deepseek coder 6.7b instruct6.7B8.3 GBFits11.1 GBFits
deepseek coder 6.7b base6.7B8.3 GBFits11.1 GBFits
Llama 2 7b hf6.7B8.3 GBFits11.1 GBFits
Yi 6B 200K6.1B4.4 GBFits7.0 GBFits
Yi 6B6.1B4.4 GBFits7.0 GBFits
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 GBFits
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 GBFits
Phi 3.5 mini instruct3.8B5.7 GBFits7.2 GBFits
Phi 3 mini 128k instruct3.8B5.7 GBFits7.2 GBFits
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 24 GB of VRAM?

195 of the 285 open models we track fit at 4-bit (Q4_K_M) with an 8K context. 161 also fit at 8-bit (Q8_0) at the same context.

What is the largest model that fits in 24 GB?

Of the models we track, the largest that fits at 4-bit with 8K context is Maxwell V1 Flash (37B), needing about 22.1 GB.

How much of 24 GB can a model actually use?

About 22.8 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

8 GB12 GB16 GB32 GB48 GB64 GB

A generic 24 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.