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

13 launchable models matching “hugging-quants” on this page. Exact, runtime-qualified revisions only.

text generationhugging-quants

gemma-2-9b-it-AWQ-INT4

gemma-2-9b-it-AWQ-INT4 is a validated text generation model.

1× GPU · 80 GB VRAM9.2B params 198.1K

text generationhugging-quants

Meta-Llama-3.1-70B-Instruct-AWQ-INT4

Meta-Llama-3.1-70B-Instruct-AWQ-INT4 is a validated text generation model.

4× GPU · 80 GB VRAM70.6B params 176K

text generationhugging-quants

Meta-Llama-3.1-8B-Instruct-AWQ-INT4

Meta-Llama-3.1-8B-Instruct-AWQ-INT4 is a validated text generation model.

1× GPU · 48 GB VRAM8B params 148.5K

text generationhugging-quants

Meta-Llama-3.1-8B-Instruct-GPTQ-INT4

Meta-Llama-3.1-8B-Instruct-GPTQ-INT4 is a validated text generation model.

1× GPU · 48 GB VRAM8B params 7.1K

text generationhugging-quants

Mixtral-8x7B-Instruct-v0.1-AWQ-INT4

Mixtral-8x7B-Instruct-v0.1-AWQ-INT4 is a validated text generation model.

2× GPU · 141 GB VRAM46.7B params 6.2K

text generationhugging-quants

Meta-Llama-3.1-8B-Instruct-BNB-NF4

Meta-Llama-3.1-8B-Instruct-BNB-NF4 is a validated text generation model.

1× GPU · 24 GB VRAM8.2B params 808

text generationhugging-quants

Meta-Llama-3.1-70B-Instruct-GPTQ-INT4

Meta-Llama-3.1-70B-Instruct-GPTQ-INT4 is a validated text generation model.

4× GPU · 80 GB VRAM70.6B params 332

text generationhugging-quants

Meta-Llama-3.1-405B-BNB-NF4

Meta-Llama-3.1-405B-BNB-NF4 is a validated text generation model.

4× GPU · 141 GB VRAM418.4B params 148

text generationhugging-quants

Meta-Llama-3.1-405B-BNB-NF4-BF16

Meta-Llama-3.1-405B-BNB-NF4-BF16 is a validated text generation model.

2× GPU · 141 GB VRAM117.2B params 65

text generationhugging-quants

Meta-Llama-3.1-8B-BNB-NF4

Meta-Llama-3.1-8B-BNB-NF4 is a validated text generation model.

1× GPU · 24 GB VRAM8.2B params 47

text generationhugging-quants

Meta-Llama-3.1-405B-Instruct-BNB-NF4

Meta-Llama-3.1-405B-Instruct-BNB-NF4 is a validated text generation model.

4× GPU · 141 GB VRAM422.8B params 42

text generationhugging-quants

Meta-Llama-3.1-70B-BNB-NF4-BF16

Meta-Llama-3.1-70B-BNB-NF4-BF16 is a validated text generation model.

1× GPU · 80 GB VRAM21.4B params 22

text generationhugging-quants

Meta-Llama-3.1-8B-BNB-NF4-BF16

Meta-Llama-3.1-8B-BNB-NF4-BF16 is a validated text generation model.

1× GPU · 24 GB VRAM3B params 18