Skip to main content
NVIDIA
Experimental NIM: LLM & VLM
Collection
NVIDIA
Experimental NIM: LLM & VLM

Experimental NIM for large language models and vision language models.

Experimental NIM: LLM & VLM

Experimental NIM for large language models and vision language models.

Experimental NIM microservices let you try new and community models early. They are provided for evaluation and are not covered by NVIDIA AI Enterprise support. They may change or be removed. For production deployments, use Certified NIM.

Browse all categories in Experimental NIM.

How to deploy and get help: open a NIM below. Each NIM page has its own deployment instructions, documentation and support information.

113 NIM in this collection

#NIMPublisherNIM type
1Bielik-11B-v2.3-InstructspeakleashModel-Specific
2CodeLlama-13B-InstructmetaModel-Specific
3CodeLlama-34B-InstructmetaModel-Specific
4CodeLlama-70B-InstructmetaModel-Specific
5DeepSeek-Coder-V2-Lite-Instructdeepseek-aiModel-Specific
6DeepSeek-R1deepseek-aiModel-Specific
7DeepSeek-R1-Distill-Llama-70Bdeepseek-aiModel-Specific
8Deepseek-R1-Distill-Llama-8Bdeepseek-aiModel-Specific
9Deepseek-R1-Distill-Qwen-14Bdeepseek-aiModel-Specific
10Deepseek-R1-Distill-Qwen-32Bdeepseek-aiModel-Specific
11Deepseek-R1-Distill-Qwen-7Bdeepseek-aiModel-Specific
12DeepSeek-V3.1deepseek-aiModel-Specific
13DeepSeek-V3.1-Terminusdeepseek-aiModel-Specific
14DeepSeek-V3.2-Exp Containerdeepseek-aiModel-Specific
15DeepSeek-V4-Flashdeepseek-aiModel-Specific
16DeepSeek-V4-Prodeepseek-aiModel-Specific
17DiffusionGemma 4 26B A4B ITgoogleModel-Specific
18ds-r1-0528-nimtooldeepseek-aiModel-Specific
19ds-v3-0324-nimtooldeepseek-aiModel-Specific
20Eurollm-9b-instructutter-projectModel-Specific
21Gemma-2-2B-ITgoogleModel-Specific
22Gemma-2-9B-ITgoogleModel-Specific
23gemma-3-1b-itgoogleModel-Specific
24Gemma2-9B-CPT-Sahabatai-v1-InstructgotocompanyModel-Specific
25GLM-5zai-orgModel-Specific
26GLM-5.1zai-orgModel-Specific
27glm-5.3-flashzai-orgModel-Specific
28GPT-OSS-120b-TurboopenaiModel-Specific
29Granite-3.3-8b-instructibm-graniteModel-Specific
30GreenMind-Medium-14B-R1greennodeModel-Specific
31kanana-1.5-8b-instruct-2505kakaocorpModel-Specific
32Kimi K2.6 CertifiedmoonshotaiModel-Specific
33kimi-k2.5-TurbomoonshotaiModel-Specific
34Llama 3.1 Nemotron Nano VL 8B v1nvidiaModel-Specific
35Llama 4 Maverick 17B 128E InstructmetaModel-Specific
36Llama 4 Scout 17B 16E InstructmetaModel-Specific
37Llama-3-SQLCoder-8BdefogModel-Specific
38Llama-3-Swallow-70B-Instruct-v0.1tokyotech-llmModel-Specific
39Llama-3-Taiwan-70B-InstructyentinglinModel-Specific
40Llama-3.1-405b-instructmetaModel-Specific
41Llama-3.1-8b-basemetaModel-Specific
42llama-3.1-8b-instruct Early AccessmetaModel-Specific
43Llama-3.1-8b-Instruct-DGX-SparkmetaModel-Specific
44Llama-3.1-Nemotron-70B-InstructnvidiaModel-Specific
45Llama-3.1-Nemotron-Nano-4B-v1.1nvidiaModel-Specific
46llama-3.1-nemotron-nano-8b-healthcare-text2sql-v1.0nvidiaModel-Specific
47Llama-3.1-Nemotron-Nano-8B-v1nvidiaModel-Specific
48Llama-3.1-Nemotron-Ultra-253B-v1nvidiaModel-Specific
49Llama-3.1-Swallow-70B-Instruct-v0.1tokyotech-llmModel-Specific
50Llama-3.1-Swallow-8B-Instruct-v0.1tokyotech-llmModel-Specific
51Llama-3.1-Typhoon2-70B-Instructscb10xModel-Specific
52Llama-3.2-11B-Vision-InstructmetaModel-Specific
53Llama-3.2-1B-InstructmetaModel-Specific
54Llama-3.2-3B-InstructmetaModel-Specific
55Llama-3.2-90B-Vision-InstructmetaModel-Specific
56llama-3.3-nemotron-super-49b-healthcare-text2sql-v1.0nvidiaModel-Specific
57Llama-3.3-Nemotron-Super-49B-v1nvidiaModel-Specific
58Llama3.1-Typhoon2-8B-Instructscb10xModel-Specific
59meta-llama-2-13b-chatmetaModel-Specific
60meta-llama-2-70b-chatmetaModel-Specific
61meta-llama-2-7b-chatmetaModel-Specific
62Meta/Llama3-70b-instructmetaModel-Specific
63Meta/Llama3-8b-instructmetaModel-Specific
64Mimo-V2-Flash (Experimental)xiaomiModel-Specific
65minimax-m2-5minimax-aiModel-Specific
66ministral-3-14b-instruct-2512mistralaiModel-Specific
67Mistral-7B-Instruct-v0.3mistralaiModel-Specific
68mistral-large-3-675b-instruct-2512mistralaiModel-Specific
69Mistral-Medium-3.5-128bmistralaiModel-Specific
70Mistral-Nemo-12B-Instructnv-mistralaiModel-Specific
71Mistral-NeMo-Minitron-8B-Instructnv-mistralaiModel-Specific
72mistral-small-24b-instruct-2501mistralaiModel-Specific
73Mistral-Small-3.2-24B-Instruct-2506mistralaiModel-Specific
74Mixtral-8x22B-Instruct-v0.1mistralaiModel-Specific
75mixtral-8x7b-instruct-v0-1mistralaiModel-Specific
76mixtral-8x7b-instruct-v0-1mistralaiModel-Specific
77Nemotron-3-Super-120B-A12B (Experimental)nvidiaModel-Specific
78Nemotron-3-Super-120B-A12B (Turbo)nvidiaModel-Specific
79Nemotron-3.5-bolt-e4b-BF16nvidiaModel-Specific
80nemotron-4-340b-instructnvidiaModel-Specific
81Nemotron-4-340B-RewardnvidiaModel-Specific
82NVIDIA-Nemotron-Nano-12B-v2-VLnvidiaModel-Specific
83NVIDIA-Nemotron-Nano-9B-v2nvidiaModel-Specific
84NVIDIA-Nemotron-Nano-9B-v2-DGX-SparknvidiaModel-Specific
85Phi-3-Mini-4K-InstructmicrosoftModel-Specific
86phi-4-mini-instructmicrosoftModel-Specific
87Phind-CodeLlama-34B-v2-InstructphindModel-Specific
88qwen-2.5-72b-instructqwenModel-Specific
89Qwen-2.5-7B-InstructqwenModel-Specific
90Qwen2.5-Coder-32B-InstructqwenModel-Specific
91qwen3-235b-a22b-fp8qwenModel-Specific
92Qwen3-235B-A22B-Instruct-2507-FP8qwenModel-Specific
93Qwen3-32BqwenModel-Specific
94Qwen3-32B NIM for DGX SparkqwenModel-Specific
95qwen3-coder-nextqwenModel-Specific
96qwen3-next-80b-a3b-instructqwenModel-Specific
97Qwen3-Next-80B-A3B-ThinkingqwenModel-Specific
98Qwen3.5-35B-A3BqwenModel-Specific
99qwen3.6-27bqwenModel-Specific
100Qwen3.6-35B-A3BqwenModel-Specific
101Sarvam-msarvamaiModel-Specific
102silma-9b-instruct-v1.0silma-aiModel-Specific
103StarCoderBase 15.5BbigcodeModel-Specific
104Step 3.7 Flashstepfun-aiModel-Specific
105step-35-flashstepfun-aiModel-Specific
106Stockmark-2-100B-InstructstockmarkModel-Specific
107Teuken-7B-instruct-commercial-v0.4opengpt-xModel-Specific
108Model-Free NIMnvidiaModel-Free
109Multi-LLM NIMnvidiaModel-Free
110Multi-LLM NIM Early AccessnvidiaModel-Free
111SGLang Model-Free NIM ExperimentalnvidiaModel-Free
112universal-nimnvidiaModel-Free
113vLLM Model-Free NIM (Experimental)nvidiaModel-Free
Experimental NIM: LLM & VLM
Publisher
NVIDIA
UpdatedNovember 18, 2026 UTC

Modal Content

NVIDIA uses cookies to improve your experience on our web site. We and our third-party partners also use cookies and other tools to collect and record information you provide as well as information about your interactions with our websites for performance improvement, analytics, and to assist in marketing efforts. By clicking "Accept All", you consent to our use of cookies and other tools as described in our Cookie Policy. You can manage your cookie settings by clicking on "Manage Settings." By continuing to use this site or by clicking one of the buttons below, you agree to our Terms of Service (which contains important waivers). Please see our Privacy Policy for more information on our privacy practices.