Framework Laptop 13 Pro DIY Edition (Intel Core Ultra Series 3): which AI models can it run?
Estimated from the specifications below. Choose the memory size you have or plan to buy, then read the table for that size.
Specifications
- Brand
- Framework
- Year
- 2026
- Chip
- Intel Core Ultra X7 358H or Core Ultra X9 388H
- Processor
- Core Ultra X7 358H or X9 388H (16 threads)
- Graphics
- Intel Arc B390 (integrated)
- Memory type
- LPDDR5X (LPCAMM2)
- Memory options
- 64 GB
- Memory bandwidth
- 119.5 GB/s
Sources: https://frame.work/laptop13pro?tab=specs, https://www.intel.com/content/www/us/en/products/sku/245527/intel-core-ultra-x7-processor-358h-18m-cache-up-to-4-80-ghz/specifications.html
Derived peak: 128 bits (two 64-bit channels, per Intel) x 7467 MT/s / 8 = 119.5GB/s, using the 7467 MT/s Framework states for these two chips. The page also lists a Core Ultra 5 325 at up to 6800 MT/s (about 108.8GB/s by the same arithmetic); that variant has no row here.
With 64 GB of memory
About 60 GB of it can hold a model.
| Model | Fit | Needs (GB) | Writing speed (tokens per second) | Speed | Quality | Basis |
|---|---|---|---|---|---|---|
| Llama 3.2 3B llama3.2:3b |
Fits | 5 | 21 to 39 | Fast | not measured yet | Estimated |
| Qwen3 4B qwen3:4b · thinks first |
Fits | 6 | 17 to 31 | Fast | not measured yet | Estimated |
| Gemma 3 4B gemma3:4b |
Fits | 6.7 | 13 to 24 | Fast | not measured yet | Estimated |
| Mistral 7B v0.3 mistral:7b |
Fits | 7.8 | 9.5 to 18 | Unclear could be Moderate or Fast | not measured yet | Estimated |
| Llama 3.1 8B llama3.1:8b |
Fits | 8.3 | 8.5 to 16 | Unclear could be Moderate or Fast | not measured yet | Estimated |
| Qwen3 8B qwen3:8b · thinks first |
Fits | 8.9 | 8 to 15 | Unclear could be Moderate or Fast | not measured yet | Estimated |
| Gemma 3 12B gemma3:12b |
Fits | 15.9 | 5.2 to 9.6 | Moderate | not measured yet | Estimated |
| DeepSeek-R1 Distill Qwen 14B deepseek-r1:14b · thinks first |
Fits | 13.7 | 4.6 to 8.6 | Unclear could be Slow or Moderate | not measured yet | Estimated |
| Phi-4 14B phi4:14b |
Fits | 13.9 | 4.6 to 8.5 | Unclear could be Slow or Moderate | not measured yet | Estimated |
| Qwen3 14B qwen3:14b · thinks first |
Fits | 13.4 | 4.5 to 8.4 | Unclear could be Slow or Moderate | not measured yet | Estimated |
| gpt-oss 20B gpt-oss:20b · thinks first |
Fits | 16.5 | 10 to 19 | Fast | not measured yet | Estimated |
| Gemma 3 27B gemma3:27b |
Fits | 27.2 | 2.5 to 4.6 | Slow | not measured yet | Estimated |
| Qwen3 30B (A3B) qwen3:30b · thinks first |
Fits | 22.6 | 12 to 23 | Fast | 9.3/10 | Estimated |
| Qwen3 32B qwen3:32b · thinks first |
Fits | 26.3 | 2.1 to 3.9 | Slow | not measured yet | Estimated |
| Llama 3.1 70B llama3.1:70b |
Fits | 51.5 | 1 to 1.8 | Slow | not measured yet | Estimated |
| gpt-oss 120B gpt-oss:120b |
Won't fit | 70.5 | not known | n/a | not measured yet | Estimated |
Models marked "thinks first" can write out their reasoning before they answer, so a job takes longer than the speed alone suggests.
Speed is the speed of writing an answer, shown as a range. Reading speed is not estimated. How the estimates work · How close they are · Back to the finder