Can I run this on that?

70 pair pages · 20 fit entirely

• Qwen3-0.6B
• Qwen2.5-0.5B-Instruct
• Qwen3.5-4B
• Qwen2.5-1.5B-Instruct
• Qwen3.5-2B
• Qwen2.5-3B-Instruct

Every model the NVIDIA GeForce GTX 1650 runs →

70 pair pages · 27 fit entirely

• Qwen3-0.6B
• Qwen2.5-0.5B-Instruct
• Qwen2.5-7B-Instruct
• Qwen3.5-4B
• Qwen3-4B
• Qwen2.5-1.5B-Instruct

Every model the NVIDIA GeForce GTX 1660 runs →

70 pair pages · 34 fit entirely

• Qwen3-0.6B
• Qwen3-VL-8B-Instruct
• Qwen3-8B
• Qwen3.5-9B
• Qwen2.5-0.5B-Instruct
• Qwen2.5-7B-Instruct

Every model the NVIDIA GeForce RTX 3070 Ti runs →

70 pair pages · 34 fit entirely

• Qwen3-0.6B
• Qwen3-VL-8B-Instruct
• Qwen3-8B
• Qwen3.5-9B
• Qwen2.5-0.5B-Instruct
• Qwen2.5-7B-Instruct

Every model the AMD Radeon RX 9060 XT 8GB runs →

70 pair pages · 34 fit entirely

• Qwen3-0.6B
• Qwen3-VL-8B-Instruct
• Qwen3-8B
• Qwen3.5-9B
• Qwen2.5-0.5B-Instruct
• Qwen2.5-7B-Instruct

Every model the NVIDIA GeForce RTX 4060 Ti 8GB runs →

70 pair pages · 34 fit entirely

• Qwen3-0.6B
• Qwen3-VL-8B-Instruct
• Qwen3-8B
• Qwen3.5-9B
• Qwen2.5-0.5B-Instruct
• Qwen2.5-7B-Instruct

Every model the AMD Radeon RX 7600 runs →

70 pair pages · 34 fit entirely

• Qwen3-0.6B
• Qwen3-VL-8B-Instruct
• Qwen3-8B
• Qwen3.5-9B
• Qwen2.5-0.5B-Instruct
• Qwen2.5-7B-Instruct

Every model the NVIDIA GeForce RTX 2060 SUPER runs →

70 pair pages · 34 fit entirely

• Qwen3-0.6B
• Qwen3-VL-8B-Instruct
• Qwen3-8B
• Qwen3.5-9B
• Qwen2.5-0.5B-Instruct
• Qwen2.5-7B-Instruct

Every model the NVIDIA GeForce RTX 5070 Laptop GPU runs →

70 pair pages · 34 fit entirely

• Qwen3-0.6B
• Qwen3-VL-8B-Instruct
• Qwen3-8B
• Qwen3.5-9B
• Qwen2.5-0.5B-Instruct
• Qwen2.5-7B-Instruct

Every model the NVIDIA GeForce RTX 3080 Laptop GPU runs →

70 pair pages · 36 fit entirely

• Qwen3-0.6B
• Qwen3-VL-8B-Instruct
• Qwen3-8B
• Qwen3.5-9B
• Qwen2.5-0.5B-Instruct
• Qwen2.5-7B-Instruct

Every model the NVIDIA GeForce RTX 2080 Ti runs →

70 pair pages · 39 fit entirely

• Qwen3-0.6B
• Qwen3-VL-8B-Instruct
• Qwen3-8B
• Qwen3.5-9B
• Qwen2.5-0.5B-Instruct
• Qwen2.5-7B-Instruct

Every model the NVIDIA GeForce RTX 4070 runs →

70 pair pages · 39 fit entirely

• Qwen3-0.6B
• Qwen3-VL-8B-Instruct
• Qwen3-8B
• Qwen3.5-9B
• Qwen2.5-0.5B-Instruct
• Qwen2.5-7B-Instruct

Every model the NVIDIA GeForce RTX 3080 12GB runs →

70 pair pages · 39 fit entirely

• Qwen3-0.6B
• Qwen3-VL-8B-Instruct
• Qwen3-8B
• Qwen3.5-9B
• Qwen2.5-0.5B-Instruct
• Qwen2.5-7B-Instruct

Every model the NVIDIA GeForce RTX 2060 12GB runs →

70 pair pages · 40 fit entirely

• Qwen3-0.6B
• Qwen3-VL-8B-Instruct
• Qwen3-8B
• Qwen3.5-9B
• Qwen2.5-0.5B-Instruct
• Qwen2.5-7B-Instruct

Every model the NVIDIA GeForce RTX 5080 runs →

70 pair pages · 40 fit entirely

• Qwen3-0.6B
• Qwen3-VL-8B-Instruct
• Qwen3-8B
• Qwen3.5-9B
• Qwen2.5-0.5B-Instruct
• Qwen2.5-7B-Instruct

Every model the AMD Radeon RX 9060 XT 16GB runs →

70 pair pages · 40 fit entirely

• Qwen3-0.6B
• Qwen3-VL-8B-Instruct
• Qwen3-8B
• Qwen3.5-9B
• Qwen2.5-0.5B-Instruct
• Qwen2.5-7B-Instruct

Every model the Intel Arc A770 (16GB) runs →

70 pair pages · 40 fit entirely

• Qwen3-0.6B
• Qwen3-VL-8B-Instruct
• Qwen3-8B
• Qwen3.5-9B
• Qwen2.5-0.5B-Instruct
• Qwen2.5-7B-Instruct

Every model the AMD Radeon RX 6900 XT runs →

70 pair pages · 44 fit entirely

• Qwen3-0.6B
• Qwen3-VL-8B-Instruct
• gemma-4-26B-A4B-it
• Qwen3-8B
• Qwen3.5-9B
• Qwen2.5-0.5B-Instruct

Every model the AMD Radeon RX 7900 XT runs →

70 pair pages · 56 fit entirely

• Qwen3-0.6B
• Qwen3-VL-8B-Instruct
• gemma-4-26B-A4B-it
• Qwen3-8B
• gemma-4-31B-it
• Qwen3.5-9B

Every model the NVIDIA GeForce RTX 3090 Ti runs →

70 pair pages · 56 fit entirely

• Qwen3-0.6B
• Qwen3-VL-8B-Instruct
• gemma-4-26B-A4B-it
• Qwen3-8B
• gemma-4-31B-it
• Qwen3.5-9B

Every model the NVIDIA GeForce RTX 5090 Laptop GPU runs →

70 pair pages · 56 fit entirely

• Qwen3-0.6B
• Qwen3-VL-8B-Instruct
• gemma-4-26B-A4B-it
• Qwen3-8B
• gemma-4-31B-it
• Qwen3.5-9B

Every model the Apple M6 runs →

70 pair pages · 56 fit entirely

• Qwen3-0.6B
• Qwen3-VL-8B-Instruct
• gemma-4-26B-A4B-it
• Qwen3-8B
• gemma-4-31B-it
• Qwen3.5-9B

Every model the Apple M1 Pro runs →

70 pair pages · 56 fit entirely

• Qwen3-0.6B
• Qwen3-VL-8B-Instruct
• gemma-4-26B-A4B-it
• Qwen3-8B
• gemma-4-31B-it
• Qwen3.5-9B

Every model the AMD Radeon PRO W7900 runs →

70 pair pages · 56 fit entirely

• Qwen3-0.6B
• Qwen3-VL-8B-Instruct
• gemma-4-26B-A4B-it
• Qwen3-8B
• gemma-4-31B-it
• Qwen3.5-9B

Every model the Apple M5 Pro runs →

70 pair pages · 58 fit entirely

• Qwen3-0.6B
• Qwen3-VL-8B-Instruct
• gemma-4-26B-A4B-it
• Qwen3-8B
• gemma-4-31B-it
• Qwen3.5-9B

Every model the NVIDIA H100 80GB PCIe runs →

70 pair pages · 59 fit entirely

• Qwen3-0.6B
• Qwen3-VL-8B-Instruct
• gemma-4-26B-A4B-it
• Qwen3-8B
• gemma-4-31B-it
• Qwen3.5-9B

Every model the Apple M3 Max runs →

70 pair pages · 59 fit entirely

• Qwen3-0.6B
• Qwen3-VL-8B-Instruct
• gemma-4-26B-A4B-it
• Qwen3-8B
• gemma-4-31B-it
• Qwen3.5-9B

Every model the Apple M1 Ultra runs →

70 pair pages · 63 fit entirely

• Qwen3-0.6B
• Qwen3-VL-8B-Instruct
• gemma-4-26B-A4B-it
• Qwen3-8B
• gemma-4-31B-it
• Qwen3.5-9B

Every model the AMD Instinct MI300X Accelerator runs →

70 pair pages · 64 fit entirely

• Qwen3-0.6B
• Qwen3-VL-8B-Instruct
• gemma-4-26B-A4B-it
• Qwen3-8B
• gemma-4-31B-it
• Qwen3.5-9B

Every model the AMD Instinct MI355X runs →

70 pair pages · 69 fit entirely

• Qwen3-0.6B
• Qwen3-VL-8B-Instruct
• gemma-4-26B-A4B-it
• Qwen3-8B
• gemma-4-31B-it
• Qwen3.5-9B

Every model the Apple M3 Ultra runs →