Home/Can I run

Direct answers

Can my machine run it?

One page per pairing, each with a yes or a no at the top and the arithmetic underneath. When the answer is no, the page says what to run instead and what it would cost to fix. For anything not listed here, the calculator covers every model and every device we track.

GeForce RTX 5090

32 GB · 1792 GB/s · Desktop GPU — runs 31 of these 34 models at a quantisation worth using.

Qwen3 8B Qwen3.5 9B Qwen2.5 7B Instruct Gemma 4 31B Instruct Gemma 4 26B A4B Instruct Qwen2.5 VL 7B Instruct Qwen2.5 1.5B Instruct Qwen2.5 3B Instruct Qwen3.5 4B OTel 2.0 LLM 31B Instruct Llama 3.2 1B Instruct GPT OSS 20B Qwen3 4B Llama 3.1 8B Instruct GPT OSS 120B Gemma 4 E4B Instruct Qwen3 32B DeepSeek V4 Flash 0731 Qwen3 1.7B Gemma 4 E2B Instruct Gemma 4 12B Instruct Gemma 3 1B Instruct Mistral 7B Instruct V0.3 Qwen3.5 2B Qwen2.5 14B Instruct Qwen3.5 27B Qwen3.5 35B A3B Qwen3 30B A3B Qwen2.5 32B Instruct GLM 4.7 Flash Qwen3 1.7B Base TinyLlama 1.1B Chat V1.0 DeepSeek R1 Qwen3 14B

GeForce RTX 5080

16 GB · 960 GB/s · Desktop GPU — runs 23 of these 34 models at a quantisation worth using.

GeForce RTX 5070 Ti

16 GB · 896 GB/s · Desktop GPU — runs 23 of these 34 models at a quantisation worth using.

GeForce RTX 5070

12 GB · 672 GB/s · Desktop GPU — runs 22 of these 34 models at a quantisation worth using.

GeForce RTX 5060 Ti 16GB

16 GB · 448 GB/s · Desktop GPU — runs 23 of these 34 models at a quantisation worth using.

GeForce RTX 5060

8 GB · 448 GB/s · Desktop GPU — runs 19 of these 34 models at a quantisation worth using.

GeForce RTX 4090

24 GB · 1008 GB/s · Desktop GPU — runs 31 of these 34 models at a quantisation worth using.

GeForce RTX 4080 SUPER

16 GB · 736 GB/s · Desktop GPU — runs 23 of these 34 models at a quantisation worth using.

GeForce RTX 4070 Ti SUPER

16 GB · 672 GB/s · Desktop GPU — runs 23 of these 34 models at a quantisation worth using.

GeForce RTX 4070 SUPER

12 GB · 504 GB/s · Desktop GPU — runs 22 of these 34 models at a quantisation worth using.

GeForce RTX 4070

12 GB · 504 GB/s · Desktop GPU — runs 22 of these 34 models at a quantisation worth using.

GeForce RTX 4060 Ti 16GB

16 GB · 288 GB/s · Desktop GPU — runs 23 of these 34 models at a quantisation worth using.

GeForce RTX 4060 Ti 8GB

8 GB · 288 GB/s · Desktop GPU — runs 19 of these 34 models at a quantisation worth using.

GeForce RTX 4060

8 GB · 272 GB/s · Desktop GPU — runs 19 of these 34 models at a quantisation worth using.

GeForce RTX 3090

24 GB · 936 GB/s · Desktop GPU — runs 31 of these 34 models at a quantisation worth using.

GeForce RTX 3080 10GB

10 GB · 760 GB/s · Desktop GPU — runs 21 of these 34 models at a quantisation worth using.

GeForce RTX 3070

8 GB · 448 GB/s · Desktop GPU — runs 19 of these 34 models at a quantisation worth using.

GeForce RTX 3060 12GB

12 GB · 360 GB/s · Desktop GPU — runs 22 of these 34 models at a quantisation worth using.

GeForce RTX 3050 8GB

8 GB · 224 GB/s · Desktop GPU — runs 19 of these 34 models at a quantisation worth using.

GeForce RTX 4090 Laptop

16 GB · 576 GB/s · Laptop GPU — runs 23 of these 34 models at a quantisation worth using.

GeForce RTX 4060 Laptop

8 GB · 256 GB/s · Laptop GPU — runs 19 of these 34 models at a quantisation worth using.

Radeon RX 9070 XT

16 GB · 645 GB/s · Desktop GPU — runs 23 of these 34 models at a quantisation worth using.

Radeon RX 7900 XTX

24 GB · 960 GB/s · Desktop GPU — runs 31 of these 34 models at a quantisation worth using.

Radeon RX 7800 XT

16 GB · 624 GB/s · Desktop GPU — runs 23 of these 34 models at a quantisation worth using.

Radeon RX 7600 XT

16 GB · 288 GB/s · Desktop GPU — runs 23 of these 34 models at a quantisation worth using.

Arc B580

12 GB · 456 GB/s · Desktop GPU — runs 22 of these 34 models at a quantisation worth using.

Arc A770 16GB

16 GB · 560 GB/s · Desktop GPU — runs 23 of these 34 models at a quantisation worth using.

Apple M4 16GB

16 GB · 120 GB/s · Unified memory — runs 22 of these 34 models at a quantisation worth using.

Apple M4 24GB

24 GB · 120 GB/s · Unified memory — runs 28 of these 34 models at a quantisation worth using.

Apple M4 Pro 24GB

24 GB · 273 GB/s · Unified memory — runs 28 of these 34 models at a quantisation worth using.

Apple M4 Pro 48GB

48 GB · 273 GB/s · Unified memory — runs 31 of these 34 models at a quantisation worth using.

Apple M4 Max 36GB

36 GB · 546 GB/s · Unified memory — runs 31 of these 34 models at a quantisation worth using.

Apple M4 Max 128GB

128 GB · 546 GB/s · Unified memory — runs 32 of these 34 models at a quantisation worth using.

Apple M3 Max 36GB

36 GB · 400 GB/s · Unified memory — runs 31 of these 34 models at a quantisation worth using.

Apple M1 Max 32GB

32 GB · 400 GB/s · Unified memory — runs 31 of these 34 models at a quantisation worth using.

Ryzen AI Max+ 395 128GB

128 GB · 256 GB/s · Unified memory — runs 32 of these 34 models at a quantisation worth using.