GPU Vault model library

Find a model. Launch it on the right GPU.

Browse currently supported Hugging Face and official ComfyUI models, compare the hardware profile, and review a live GPU offer before spending credits.

Sort

Launchable models

9 launchable models matching “unsloth” on this page. Exact, runtime-qualified revisions only.

text generationunsloth

mistral-7b-v0.3-bnb-4bit

mistral-7b-v0.3-bnb-4bit is a validated text generation model.

1× GPU · 24 GB VRAM7.5B params 375.3K

text generationunsloth

Qwen2.5-14B-bnb-4bit

Qwen2.5-14B-bnb-4bit is a validated text generation model.

1× GPU · 40 GB VRAM15.2B params 294.2K

text generationunsloth

Qwen2.5-7B-Instruct

Qwen2.5-7B-Instruct is a validated text generation model.

1× GPU · 40 GB VRAM7.6B params 263K

text generationunsloth

Llama-3.2-1B-Instruct

Llama-3.2-1B-Instruct is a validated text generation model.

1× GPU · 16 GB VRAM1.2B params 248.9K

text generationunsloth

Meta-Llama-3.1-8B-Instruct

Meta-Llama-3.1-8B-Instruct is a validated text generation model.

1× GPU · 40 GB VRAM8B params 206.9K

text generationunsloth

Qwen2.5-Coder-7B-Instruct

Qwen2.5-Coder-7B-Instruct is a validated text generation model.

1× GPU · 40 GB VRAM7.6B params 183.5K

text generationunsloth

Qwen3-14B-unsloth-bnb-4bit

Qwen3-14B-unsloth-bnb-4bit is a validated text generation model.

1× GPU · 40 GB VRAM15.2B params 157.1K

text generationunsloth

Llama-3.2-3B-Instruct

Llama-3.2-3B-Instruct is a validated text generation model.

1× GPU · 24 GB VRAM3.2B params 152.2K

text generationunsloth

Qwen2.5-7B-Instruct-bnb-4bit

Qwen2.5-7B-Instruct-bnb-4bit is a validated text generation model.

1× GPU · 24 GB VRAM7.8B params 132.4K