Razer Blade 18 (2026) with RTX 5080: 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
- Razer
- Year
- 2026
- Chip
- Intel Core Ultra 9 290HX Plus
- Processor
- Intel Core Ultra 9 290HX Plus (up to 5.5GHz)
- Graphics
- NVIDIA GeForce RTX 5080 Laptop GPU
- Memory type
- DDR5-6400 (2 slots)
- Memory options
- 128 GB
- Graphics memory
- 16 GB
- Memory bandwidth
- 896 GB/s
Sources: https://www.razer.com/gaming-laptops/razer-blade-18, https://www.nvidia.com/en-us/geforce/laptops/50-series/
Razer lists "up to 128GB DDR5 6400MHz (2 slots)" and states 16GB VRAM; smaller memory sizes are not itemised. The 2026 column also lists an RTX 5070 Ti 12GB. GPU bandwidth from NVIDIA's RTX 50 laptop page.
With 128 GB of memory
About 16 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 | 157 to 291 | Fast | not measured yet | Estimated |
| Qwen3 4B qwen3:4b · thinks first |
Fits | 6 | 125 to 233 | Fast | not measured yet | Estimated |
| Gemma 3 4B gemma3:4b |
Fits | 6.7 | 95 to 176 | Fast | not measured yet | Estimated |
| Mistral 7B v0.3 mistral:7b |
Fits | 7.8 | 71 to 132 | Fast | not measured yet | Estimated |
| Llama 3.1 8B llama3.1:8b |
Fits | 8.3 | 64 to 119 | Fast | not measured yet | Estimated |
| Qwen3 8B qwen3:8b · thinks first |
Fits | 8.9 | 60 to 112 | Fast | not measured yet | Estimated |
| Gemma 3 12B gemma3:12b |
Tight | 15.9 | 39 to 72 | Fast | not measured yet | Estimated |
| DeepSeek-R1 Distill Qwen 14B deepseek-r1:14b · thinks first |
Fits | 13.7 | 35 to 65 | Fast | not measured yet | Estimated |
| Phi-4 14B phi4:14b |
Fits | 13.9 | 34 to 64 | Fast | not measured yet | Estimated |
| Qwen3 14B qwen3:14b · thinks first |
Fits | 13.4 | 34 to 63 | Fast | not measured yet | Estimated |
| gpt-oss 20B gpt-oss:20b · thinks first Part of the model runs from system memory, which is much slower. |
Partial offload (slow) | 16.5 | 12 to 22 | Fast | not measured yet | Estimated |
| Gemma 3 27B gemma3:27b Part of the model runs from system memory, which is much slower. |
Partial offload (slow) | 27.2 | 2.8 to 5.1 | Unclear could be Slow or Moderate | not measured yet | Estimated |
| Qwen3 30B (A3B) qwen3:30b · thinks first Part of the model runs from system memory, which is much slower. |
Partial offload (slow) | 22.6 | 14 to 25 | Fast | 9.3/10 | Estimated |
| Qwen3 32B qwen3:32b · thinks first Part of the model runs from system memory, which is much slower. |
Partial offload (slow) | 26.3 | 2.4 to 4.4 | Slow | not measured yet | Estimated |
| Llama 3.1 70B llama3.1:70b Part of the model runs from system memory, which is much slower. |
Partial offload (slow) | 51.5 | 1.1 to 2 | Slow | not measured yet | Estimated |
| gpt-oss 120B gpt-oss:120b · thinks first Part of the model runs from system memory, which is much slower. |
Partial offload (slow) | 70.5 | 10 to 18 | Unclear could be Moderate or Fast | 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