Xlarge

AI21-Jamba-Large-1.5 specs, VRAM requirements, and which GPUs can run it.

Athene-70B-Preview specs, VRAM requirements, and which GPUs can run it.

Athene-V2-Agent specs, VRAM requirements, and which GPUs can run it.

bloomz specs, VRAM requirements, and which GPUs can run it.

DeepSeek-Coder-V2-Instruct specs, VRAM requirements, and which GPUs can run it.

DeepSeek-Coder-V2-Instruct-0724 specs, VRAM requirements, and which GPUs can run it.

DeepSeek-R1-0528 specs, VRAM requirements, and which GPUs can run it.

DeepSeek-R1-0528-NVFP4 specs, VRAM requirements, and which GPUs can run it.

DeepSeek-R1-0528-NVFP4-v2 specs, VRAM requirements, and which GPUs can run it.

DeepSeek-R1-NVFP4 specs, VRAM requirements, and which GPUs can run it.

DeepSeek-V2 specs, VRAM requirements, and which GPUs can run it.

Deepseek-V2 Pro specs, VRAM requirements, and which GPUs can run it.

DeepSeek-V2-Chat specs, VRAM requirements, and which GPUs can run it.

DeepSeek-V2-Chat-0628 specs, VRAM requirements, and which GPUs can run it.

DeepSeek-V2.5 specs, VRAM requirements, and which GPUs can run it.

DeepSeek-V3-0324 specs, VRAM requirements, and which GPUs can run it.

DeepSeek-V3-0324-NVFP4 specs, VRAM requirements, and which GPUs can run it.

DeepSeek-V3.1-NVFP4 specs, VRAM requirements, and which GPUs can run it.

DeepSeek-V3.2 specs, VRAM requirements, and which GPUs can run it.

DeepSeek-V3.2-NVFP4 specs, VRAM requirements, and which GPUs can run it.

gpt-oss-120b specs, VRAM requirements, and which GPUs can run it.

Llama 3.1 70B specs, VRAM requirements, and which GPUs can run it. The sweet spot for local reasoning.

Llama-3.1-405B-Instruct specs, VRAM requirements, and which GPUs can run it.

Llama-3.1-405B-Instruct-FP8 specs, VRAM requirements, and which GPUs can run it.

Llama-3.1-70B-Instruct specs, VRAM requirements, and which GPUs can run it.

llama-3.3-70b-instruct-awq specs, VRAM requirements, and which GPUs can run it.

Meta-Llama-3-70B-Instruct specs, VRAM requirements, and which GPUs can run it.

Meta-Llama-3.1-70B-Instruct specs, VRAM requirements, and which GPUs can run it.

MiniMax-M2-AWQ specs, VRAM requirements, and which GPUs can run it.

MiniMax-M2.5 specs, VRAM requirements, and which GPUs can run it.

Qwen 2.5 72B specs, VRAM requirements, and which GPUs can run it. Strong on benchmarks, competitive with Llama 70B.

Qwen 2.5 72B Instruct specs, VRAM requirements, and which GPUs can run it.

Qwen1.5-110B-Chat-AWQ specs, VRAM requirements, and which GPUs can run it.

Qwen2 72B specs, VRAM requirements, and which GPUs can run it.

Qwen2.5-72B-Instruct specs, VRAM requirements, and which GPUs can run it.

Qwen2.5-72B-Instruct-AWQ specs, VRAM requirements, and which GPUs can run it.

Qwen3-235B-A22B specs, VRAM requirements, and which GPUs can run it.

Qwen3-235B-A22B-Instruct-2507-FP8 specs, VRAM requirements, and which GPUs can run it.

Qwen3-235B-A22B-NVFP4 specs, VRAM requirements, and which GPUs can run it.

Qwen3-Coder-Next specs, VRAM requirements, and which GPUs can run it.

Qwen3-Coder-Next-Base specs, VRAM requirements, and which GPUs can run it.

Qwen3-Coder-Next-FP8 specs, VRAM requirements, and which GPUs can run it.

Qwen3-Next-80B-A3B-Instruct specs, VRAM requirements, and which GPUs can run it.

Qwen3-Next-80B-A3B-Instruct-FP8 specs, VRAM requirements, and which GPUs can run it.

Step-3.5-Flash specs, VRAM requirements, and which GPUs can run it.