Every memory option compared, 120 GB/s memory bandwidth. Laptops with this chip include ASUS Zenbook S 16, HP OmniBook Ultra 14. Updated 2 November 2026.
Ryzen AI 300 is sold with 16, 24, 32 GB of memory. Counting the 31 models tracked here: 16 GB runs 12 models well; 24 GB runs 15 models well; 32 GB runs 19 models well. Memory bandwidth is 120 GB/s, about 1.5 times the memory speed of an everyday laptop without an AI chip (80 GB/s), so the same model generates words proportionally faster. These laptops share their RAM between the processor and the built-in graphics, and the RAM is soldered, so it cannot be upgraded later. Windows also needs its share, so roughly 70% of the RAM is realistically available for a model, and the memory you buy decides which models load at all.
| Model | 16 GB | 24 GB | 32 GB |
|---|---|---|---|
| LTX-2.3 | No | No | Slow about 42 min |
| Gemma 4 31B | No | No | Slow 2/s |
| DeepSeek R1 32B | No | No | Slow 2/s |
| Qwen3 Coder 30B | No | No | Tight 14/s |
| Qwen 3.6 27B | No | No | Slow 3/s |
| Gemma 4 26B A4B | No | No | Tight 11/s |
| Z-Image Turbo 6B | No | Slow about 9 min | Good about 5 min |
| Wan 2.2 5B | No | Slow about 2.5 hours | Good about 1.3 hours |
| gpt-oss 20B | No | Tight 11/s | Great 12/s |
| ACE-Step 1.5 | Slow about 10 min | Good about 5 min | Good about 5 min |
| FLUX.2 klein 4B | Slow about 6 min | Good about 3 min | Good about 3 min |
| Phi-4 14B | Slow 5/s | Slow 6/s | Slow 6/s |
| Stable Diffusion XL | Good about 2 min | Good about 2 min | Good about 2 min |
| Qwen3 TTS 1.7B | Good about 2 min | Good about 2 min | Good about 2 min |
| Gemma 4 12B | Tight 7/s | Good 7/s | Good 7/s |
| Gemma 4 E4B | Great 17/s | Great 17/s | Great 17/s |
| Qwen 3.5 9B | Good 8/s | Good 8/s | Good 8/s |
| Qwen3 VL 8B | Good 9/s | Good 9/s | Good 9/s |
| DeepSeek R1 8B | Good 11/s | Good 11/s | Good 11/s |
| Qwen2.5 Coder 7B | Great 11/s | Great 11/s | Great 11/s |
| Gemma 4 E2B | Great 27/s | Great 27/s | Great 27/s |
| Whisper large-v3 turbo | Good about 2 min | Good about 2 min | Good about 2 min |
| Qwen 3.5 4B | Great 17/s | Great 17/s | Great 17/s |
| Kokoro TTS | Good about 20 s | Good about 20 s | Good about 20 s |
Text models show words a second. Image, video and voice models show the time per job (image, 4 second clip, minute of speech or similar).
As an Amazon Associate I earn from qualifying purchases.
About 11 GB is usable for models. The largest chat or coding model that fits is Gemma 4 12B (8.5 GB), generating about 7 words a second with 2.7 GB to spare. The quickest is Gemma 4 E2B at about 27 words a second. Closest miss: gpt-oss 20B, which needs about 15.2 GB (4 GB more than this configuration can give the GPU).
Find Ryzen AI 300 laptops with 16 GB on Amazon
About 17 GB is usable for models. The largest chat or coding model that fits is gpt-oss 20B (15.2 GB), generating about 11 words a second with 1.6 GB to spare. The quickest is Gemma 4 E2B at about 27 words a second. Closest miss: Gemma 4 26B A4B, which needs about 19.4 GB (3 GB more than this configuration can give the GPU).
Find Ryzen AI 300 laptops with 24 GB on Amazon
About 22 GB is usable for models. The largest chat or coding model that fits is Qwen3 Coder 30B (20.4 GB), generating about 14 words a second with 2 GB to spare. The quickest is Gemma 4 E2B at about 27 words a second. Closest miss: Qwen 3.5 35B A3B, which needs about 23.6 GB (1 GB more than this configuration can give the GPU).
For everyday chat, 16 GB runs 12 of 31 models well. 24 GB to 32 GB unlocks 4 more: Gemma 4 26B A4B, Qwen3 Coder 30B, Z-Image Turbo 6B, Wan 2.2 5B.
No. It needs about 21.5 GB of usable memory and this chip's largest option is 32 GB.
16 GB cannot run gpt-oss 20B; 24 GB runs gpt-oss 20B at about 11 words a second; 32 GB runs gpt-oss 20B at about 12 words a second.
As an Amazon Associate I earn from qualifying purchases.
Unlocks 1 more: Phi-4 14B.
Unlocks 8 more: Qwen 3.5 35B A3B, Qwen 3.5 122B A10B, gpt-oss 120B, Qwen 3.6 27B and more.
Unlocks 8 more: Qwen 3.5 35B A3B, Gemma 4 31B, Qwen 3.6 27B, Qwen 3.6 35B A3B and more.