What can Razer Blade 16 (2025, RTX 5090 Mobile) run?
Build: Razer Blade 16 (2025, RTX 5090 Mobile) + — + 64 GB RAM (windows)
Runs comfortably184 models
Full-VRAM resident, with room for context. No compromises.
Quant: Q4_K_MContext: 8,192VRAM: 2.4 GBHeadroom: 21.6 GB1705tok/sEstimated
Quant: FP16Context: 8,192VRAM: 19.8 GBHeadroom: 4.2 GBollama run llama3.1:8b39tok/sEstimated
ollama run llama3.1:8bQuant: Q8_0Context: 8,192VRAM: 14.4 GBHeadroom: 9.6 GBollama run qwen3:8b73tok/sEstimated
ollama run qwen3:8bQuant: Q4_K_MContext: 8,192VRAM: 15.8 GBHeadroom: 8.2 GBollama run gemma4:12b85tok/sEstimated
ollama run gemma4:12bQuant: Q4_K_MContext: 8,192VRAM: 13.2 GBHeadroom: 10.8 GBollama run qwen3.5:9b114tok/sEstimated
ollama run qwen3.5:9bQuant: MXFP4Context: 2,048VRAM: 19.1 GBHeadroom: 4.9 GBollama run gpt-oss:20b30tok/sEstimated
ollama run gpt-oss:20bQuant: Q8_0Context: 8,192VRAM: 6.9 GBHeadroom: 17.1 GBollama run llama3.2:3b194tok/sEstimated
ollama run llama3.2:3bQuant: Q4_K_MContext: 8,192VRAM: 3.6 GBHeadroom: 20.4 GB602tok/sEstimated
Quant: Q4_K_MContext: 8,192VRAM: 17.6 GBHeadroom: 6.4 GBollama run qwen3:14b73tok/sEstimated
ollama run qwen3:14bQuant: Q8_0Context: 8,192VRAM: 10.8 GBHeadroom: 13.2 GBollama run qwen2.5:7b83tok/sEstimated
ollama run qwen2.5:7bQuant: Q4_K_MContext: 8,192VRAM: 2.1 GBHeadroom: 21.9 GB3788tok/sEstimated
Quant: Q4_K_MContext: 2,048VRAM: 19.5 GBHeadroom: 4.5 GBollama run mistral-small:24b43tok/sEstimated
ollama run mistral-small:24bRuns with tradeoffs73 models
Tight VRAM, partial CPU offload, or context-limited.
Quant: Q8_0Context: 8,192VRAM: 50.4 GBHeadroom: 12.0 GB- • Partial CPU offload: ~52% of layers run on CPU
ollama run qwen3:30b19tok/sEstimated
- • Partial CPU offload: ~52% of layers run on CPU
ollama run qwen3:30bQuant: Q4_K_MContext: 8,192VRAM: 23.9 GBHeadroom: 0.1 GB- • Tight VRAM fit — only 0.1 GB headroom left for context growth
ollama run qwen2.5-coder:32b32tok/sEstimated
- • Tight VRAM fit — only 0.1 GB headroom left for context growth
ollama run qwen2.5-coder:32bQuant: Q4_K_MContext: 2,048VRAM: 23.0 GBHeadroom: 1.0 GB- • Tight VRAM fit — only 1.0 GB headroom left for context growth
ollama run qwen3.6:27b38tok/sEstimated
- • Tight VRAM fit — only 1.0 GB headroom left for context growth
ollama run qwen3.6:27bQuant: Q5_K_MContext: 8,192VRAM: 53.8 GBHeadroom: 8.6 GB- • Partial CPU offload: ~55% of layers run on CPU
ollama run llama3.3:70b13tok/sEstimated
- • Partial CPU offload: ~55% of layers run on CPU
ollama run llama3.3:70bQuant: Q8_0Context: 8,192VRAM: 53.5 GBHeadroom: 8.9 GB- • Partial CPU offload: ~55% of layers run on CPU
ollama run qwen3:32b18tok/sEstimated
- • Partial CPU offload: ~55% of layers run on CPU
ollama run qwen3:32bQuant: Q8_0Context: 8,192VRAM: 52.0 GBHeadroom: 10.4 GB- • Partial CPU offload: ~54% of layers run on CPU
ollama run gemma4:31b19tok/sEstimated
- • Partial CPU offload: ~54% of layers run on CPU
ollama run gemma4:31bQuant: Q4_K_MContext: 8,192VRAM: 36.8 GBHeadroom: 25.6 GB- • Partial CPU offload: ~35% of layers run on CPU
ollama run qwen3-coder:30b34tok/sEstimated
- • Partial CPU offload: ~35% of layers run on CPU
ollama run qwen3-coder:30bQuant: Q4_K_MContext: 2,048VRAM: 52.6 GBHeadroom: 9.8 GB- • Partial CPU offload: ~54% of layers run on CPU
ollama run deepseek-r1:70b15tok/sEstimated
- • Partial CPU offload: ~54% of layers run on CPU
ollama run deepseek-r1:70bWhat if you upgraded?
Hypothetical scenarios. We re-ran the compatibility engine for each.
+32 GB system RAM
~$80–150
Doubles your CPU-offload working set. Helps when models don't quite fit in VRAM.
Unlocks: 79 new tradeoff
- • Qwen 3 30B-A3B
- • Qwen 2.5 Coder 32B Instruct
- • Qwen3.6 27B
- • Llama 3.3 70B Instruct
Upgrade to NVIDIA RTX PRO 4500 Blackwell
see current pricing
32 GB VRAM (vs your 24 GB) plus a bandwidth jump from ~? GB/s to ~896 GB/s.
Unlocks: 39 new comfortable
- • Qwen 3 30B-A3B
- • Qwen 2.5 Coder 32B Instruct
- • Qwen3.6 27B
- • Qwen 3 32B
Add a second Razer Blade 16 (2025, RTX 5090 Mobile)
see current pricing
Tensor parallelism splits the model across both cards, effectively doubling VRAM. Bandwidth doesn't double — runs ~1.5× the single-card speed in practice.
Unlocks: 52 new comfortable
- • Qwen 3 30B-A3B
- • Qwen 2.5 Coder 32B Instruct
- • Qwen3.6 27B
- • Qwen 3 32B
Some links above are affiliate links. We may earn a commission at no extra cost to you. How we make money.
Won't runtop 5 popular models
Need more memory than you have. Shown for orientation.
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (38 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (38 GB) combined.
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (38 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (38 GB) combined.
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (38 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (38 GB) combined.
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (38 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (38 GB) combined.
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (38 GB) combined.
—
Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (38 GB) combined.
How to read these numbers
Want a specific benchmark we don't have? Email Contact support and we'll prioritize it.