GPU Vault model library

Launch text-generation models on dedicated GPUs.

Find validated models for chat, coding, summarization, extraction, and other private text workloads.

Sort

Text-generation models

24 launchable models on this page. Exact, runtime-qualified revisions only.

text generationQwen

Qwen3-0.6B

Qwen3-0.6B is a validated text generation model.

1× GPU · 16 GB VRAM751.6M params 28.1M

text generationQwen

Qwen3-8B

Qwen3-8B is a validated text generation model.

1× GPU · 40 GB VRAM8.2B params 12.3M

text generationtrl-internal-testing

tiny-Qwen2ForCausalLM-2.5

tiny-Qwen2ForCausalLM-2.5 is a validated text generation model.

1× GPU · 16 GB VRAM2.4M params 11.9M

text generationQwen

Qwen2.5-7B-Instruct

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

1× GPU · 40 GB VRAM7.6B params 9.8M

text generationQwen

Qwen2.5-0.5B-Instruct

Qwen2.5-0.5B-Instruct is a validated text generation model.

1× GPU · 16 GB VRAM494M params 8.7M

text generationQwen

Qwen2.5-1.5B-Instruct

Qwen2.5-1.5B-Instruct is a validated text generation model.

1× GPU · 24 GB VRAM1.5B params 7.8M

text generationmeta-llama

Llama-3.2-1B-Instruct

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

1× GPU · 16 GB VRAM1.2B params 7.4M

text generationQwen

Qwen3-4B

Qwen3-4B is a validated text generation model.

1× GPU · 24 GB VRAM4B params 6.7M

text generationmeta-llama

Llama-3.1-8B-Instruct

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

1× GPU · 40 GB VRAM8B params 6.2M

text generationdphn

dolphin-2.9.1-yi-1.5-34b

dolphin-2.9.1-yi-1.5-34b is a validated text generation model.

1× GPU · 96 GB VRAM34.4B params 4.8M

text generationQwen

Qwen3-32B

Qwen3-32B is a validated text generation model.

1× GPU · 96 GB VRAM32.8B params 4.5M

text generationQwen

Qwen2.5-3B-Instruct

Qwen2.5-3B-Instruct is a validated text generation model.

1× GPU · 24 GB VRAM3.1B params 4.3M

text generationQwen

Qwen3-4B-Instruct-2507

Qwen3-4B-Instruct-2507 is a validated text generation model.

1× GPU · 24 GB VRAM4B params 3.9M

text generationQwen

Qwen3-1.7B

Qwen3-1.7B is a validated text generation model.

1× GPU · 24 GB VRAM2B params 3.5M

text generationgoogle

gemma-3-1b-it

gemma-3-1b-it is a validated text generation model.

1× GPU · 16 GB VRAM999.9M params 3.4M

text generationEleutherAI

pythia-160m

pythia-160m is a validated text generation model.

1× GPU · 16 GB VRAM212.7M params 3.3M

text generationQwen

Qwen2.5-7B-Instruct-AWQ

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

1× GPU · 48 GB VRAM7.6B params 3.3M

text generationQwen

Qwen3-14B-AWQ

Qwen3-14B-AWQ is a validated text generation model.

1× GPU · 80 GB VRAM14.8B params 2.6M

text generationQwen

Qwen2.5-Coder-7B-Instruct

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

1× GPU · 40 GB VRAM7.6B params 2.5M

text generationQwen

Qwen3-14B

Qwen3-14B is a validated text generation model.

1× GPU · 48 GB VRAM14.8B params 2.2M

text generationQwen

Qwen2.5-32B-Instruct

Qwen2.5-32B-Instruct is a validated text generation model.

1× GPU · 96 GB VRAM32.8B params 2M

text generationQwen

Qwen2.5-14B-Instruct-AWQ

Qwen2.5-14B-Instruct-AWQ is a validated text generation model.

1× GPU · 80 GB VRAM14.8B params 2M

text generationQwen

Qwen2.5-14B-Instruct

Qwen2.5-14B-Instruct is a validated text generation model.

1× GPU · 48 GB VRAM14.8B params 2M

text generationQwen

Qwen3-8B-AWQ

Qwen3-8B-AWQ is a validated text generation model.

1× GPU · 48 GB VRAM8.2B params 2M