Explore
Models
Blueprints
GPUs
Docs
⌘K
Ctrl+K
?
Login
Models
Deploy and scale models on your GPU infrastructure of choice with NVIDIA NIM inference microservices
Optimized by NVIDIA
Launch from Hugging Face
Beta
Filters
61 models
Sort By
dateCreated:DESC
Most Recent
Qwen
qwen3.5-122b-a10b
122B MoE LLM (10B active) for coding, reasoning, multimodal chat. Agent-ready.
tool calling
+4
1d
Qwen
qwen3.5-397b-a17b
Next-gen Qwen 3.5 VLM (400B MoE) brings advanced vision, chat, RAG, and agentic capabilities.
MoE
+4
5.14M
2w
Mistral AI
mistral-large-3-675b-instruct-2512
A state-of-the-art general purpose MoE VLM ideal for chat, agentic and instruction based use cases.
language generation
+4
4.89M
3mo
Mistral AI
ministral-14b-instruct-2512
A general purpose VLM ideal for chat and instruction based use cases
language generation
+4
3.6M
3mo
DeepSeek AI
deepseek-v3.1-terminus
DeepSeek-V3.1: hybrid inference LLM with Think/Non-Think modes, stronger agents, 128K context, strict function calling.
tool calling
+3
11.9M
5mo
Speakleash
bielik-11b-v2.6-instruct
State-of-the-art model for Polish language processing tasks such as text generation, Q&A, and chatbots.
Polish
+4
450K
5mo
OpenAI
gpt-oss-20b
Smaller Mixture of Experts (MoE) text-only LLM for efficient AI reasoning and math
text-to-text
+3
6.72M
7mo
OpenAI
gpt-oss-120b
Mixture of Experts (MoE) reasoning LLM (text-only) designed to fit within 80GB GPU.
text-to-text
+3
34.08M
7mo
NVIDIA
llama-3.3-nemotron-super-49b-v1.5
High efficiency model with leading accuracy for reasoning, tool calling, chat, and instruction following.
chat
+4
4.01M
7mo
Opengpt-x
teuken-7b-instruct-commercial-v0.4
Multilingual 7B LLM, instruction-tuned on all 24 EU languages for stable, culturally aligned output.
sovereign ai
+4
401K
7mo
Moonshotai
kimi-k2-instruct
State-of-the-art open mixture-of-experts model with strong reasoning, coding, and agentic capabilities
coding
+3
19.22M
7mo
Google
gemma-3n-e4b-it
An edge computing AI model which accepts text, audio and image input, ideal for resource-constrained environments
language generation
+3
626K
7mo
Google
gemma-3n-e2b-it
An edge computing AI model which accepts text, audio and image input, ideal for resource-constrained environments
language generation
+3
549K
7mo
NVIDIA
llama-3.1-nemotron-nano-vl-8b-v1
Multi-modal vision-language model that understands text/img and creates informative responses
doc intelligence
+3
6.24M
8mo
Utter-project
eurollm-9b-instruct
State-of-the-art, multilingual model tailored to all 24 official European Union languages.
Sovereign AI
+5
5.52K
402K
8mo
Gotocompany
gemma-2-9b-cpt-sahabatai-instruct
SOTA LLM pre-trained for instruction following and proficiency in Indonesian language and its dialects.
Sovereign AI
+4
402K
8mo
Qwen
qwq-32b
Powerful reasoning model capable of thinking and reasoning, can achieve significantly enhanced performance in downstream tasks, especially hard problems.
coding
+3
3.2M
8mo
NVIDIA
llama-3.3-nemotron-super-49b-v1
High efficiency model with leading accuracy for reasoning, tool calling, chat, and instruction following.
chat
+4
1.08M
7mo
Google
gemma-3-1b-it
A lightweight, multilingual, advanced SLM text model for edge computing, resource constraint applications
Translation
+3
4.93K
439K
9mo
Microsoft
phi-4-mini-instruct
Lightweight multilingual LLM powering AI applications in latency bound, memory/compute constrained environments
chat
+3
1.91M
9mo
Microsoft
phi-4-multimodal-instruct
Cutting-edge open multimodal model exceling in high-quality reasoning from image and audio inputs.
Speech Recognition
+5
385K
9mo
Qwen
qwen2.5-7b-instruct
Chinese and English LLM targeting for language, coding, mathematics, reasoning, etc.
Chinese Language Generation
+3
1.41M
9mo
NVIDIA
usdcode
State-of-the-art LLM that answers OpenUSD knowledge queries and generates USD-Python code.
OpenUSD
+4
302K
8mo
NVIDIA
nemotron-4-mini-hindi-4b-instruct
A bilingual Hindi-English SLM for on-device inference, tailored specifically for Hindi Language.
Indic
+3
407K
9mo
Items per page
24
1
1
2
2
3
3
of 3 pages
