LLM

OpenVINO 's Collections

Visual Language Models

VLMs optimized for NPU

Image Generation

Speculative Decoding Draft Models

Speech-to-Text

LLM

LLMs optimized for NPU

Physical AI

Vision

updated 5 days ago

Collection of OpenVINO optimized LLMs

Upvote

OpenVINO/phi-2-fp16-ov

Text Generation • Updated Nov 5, 2024 • 83 • 1
OpenVINO/phi-2-int8-ov

Text Generation • Updated Oct 29, 2024 • 71
OpenVINO/mistral-7b-instruct-v0.1-fp16-ov

Text Generation • Updated Nov 11, 2024 • 20
OpenVINO/mistral-7b-instruct-v0.1-int4-ov

Text Generation • Updated Oct 29, 2024 • 98 • 1
OpenVINO/codegen25-7b-multi-fp16-ov

Text Generation • Updated Nov 5, 2024 • 93
OpenVINO/mixtral-8x7b-instruct-v0.1-int4-ov

Text Generation • Updated Nov 5, 2024 • 77 • 5
OpenVINO/Mixtral-8x7B-Instruct-v0.1-int8-ov

Text Generation • Updated Nov 5, 2024 • 29 • 4
OpenVINO/neural-chat-7b-v3-3-fp16-ov

Text Generation • Updated Nov 5, 2024 • 23
OpenVINO/neural-chat-7b-v3-3-int8-ov

Text Generation • Updated Nov 5, 2024 • 83 • 1
OpenVINO/zephyr-7b-beta-int8-ov

Text Generation • Updated Nov 5, 2024 • 27
OpenVINO/zephyr-7b-beta-int4-ov

Text Generation • Updated Nov 5, 2024 • 34
OpenVINO/dolly-v2-3b-int4-ov

Text Generation • Updated Nov 5, 2024 • 41 • 1
OpenVINO/dolly-v2-3b-int8-ov

Text Generation • Updated Nov 5, 2024 • 36
OpenVINO/dolly-v2-3b-fp16-ov

Text Generation • Updated Nov 5, 2024 • 23
OpenVINO/zephyr-7b-beta-fp16-ov

Text Generation • Updated Nov 5, 2024 • 17
OpenVINO/TinyLlama-1.1B-Chat-v1.0-fp16-ov

Text Generation • Updated Mar 10 • 78 • 2
OpenVINO/TinyLlama-1.1B-Chat-v1.0-int4-ov

Text Generation • Updated Dec 12, 2025 • 850 • 3
OpenVINO/TinyLlama-1.1B-Chat-v1.0-int8-ov

Text Generation • Updated Dec 12, 2025 • 745 • 1
OpenVINO/gpt-neox-20b-int8-ov

Text Generation • Updated Nov 5, 2024 • 39 • 1
OpenVINO/gpt-neox-20b-fp16-ov

Text Generation • Updated Nov 5, 2024 • 36
OpenVINO/gpt-j-6b-int4-ov

Text Generation • Updated Nov 5, 2024 • 33
OpenVINO/gpt-j-6b-int8-ov

Text Generation • Updated Nov 5, 2024 • 23
OpenVINO/gpt-j-6b-fp16-ov

Text Generation • Updated Nov 5, 2024 • 36
OpenVINO/falcon-7b-instruct-int4-ov

Text Generation • Updated Nov 5, 2024 • 42
OpenVINO/falcon-7b-instruct-fp16-ov

Text Generation • Updated Nov 5, 2024 • 37
OpenVINO/falcon-7b-instruct-int8-ov

Text Generation • Updated Nov 5, 2024 • 31
OpenVINO/phi-2-int4-ov

Text Generation • Updated Nov 5, 2024 • 31 • 1
OpenVINO/neural-chat-7b-v3-3-int4-ov

Text Generation • Updated Nov 5, 2024 • 34 • 1
OpenVINO/RedPajama-INCITE-Chat-3B-v1-int8-ov

Text Generation • Updated Nov 5, 2024 • 40
OpenVINO/RedPajama-INCITE-Chat-3B-v1-int4-ov

Text Generation • Updated Nov 5, 2024 • 30
OpenVINO/RedPajama-INCITE-Chat-3B-v1-fp16-ov

Text Generation • Updated Nov 5, 2024 • 45
OpenVINO/dolly-v2-7b-fp16-ov

Text Generation • Updated Nov 5, 2024 • 24
OpenVINO/Mistral-7B-Instruct-v0.2-int8-ov

Text Generation • Updated Oct 29, 2024 • 23 • 1
OpenVINO/dolly-v2-12b-int8-ov

Text Generation • Updated Nov 5, 2024 • 27 • 1
OpenVINO/Mistral-7B-Instruct-v0.2-int4-ov

Text Generation • Updated Oct 31, 2024 • 223 • 1
OpenVINO/Mistral-7B-Instruct-v0.2-fp16-ov

Text Generation • Updated Nov 5, 2024 • 24
OpenVINO/persimmon-8b-chat-int4-ov

Text Generation • Updated Nov 5, 2024 • 28
OpenVINO/persimmon-8b-chat-int8-ov

Text Generation • Updated Nov 5, 2024 • 24
OpenVINO/persimmon-8b-chat-fp16-ov

Text Generation • Updated Nov 5, 2024 • 28
OpenVINO/pythia-12b-int8-ov

Text Generation • Updated Nov 5, 2024 • 36
OpenVINO/pythia-12b-fp16-ov

Text Generation • Updated Nov 5, 2024 • 39
OpenVINO/pythia-6.9b-int4-ov

Text Generation • Updated Nov 5, 2024 • 36
OpenVINO/pythia-6.9b-int8-ov

Text Generation • Updated Nov 5, 2024 • 40
OpenVINO/pythia-6.9b-fp16-ov

Text Generation • Updated Nov 5, 2024 • 32
OpenVINO/pythia-1b-int4-ov

Text Generation • Updated Nov 5, 2024 • 32
OpenVINO/Phi-3-medium-4k-instruct-fp16-ov

Text Generation • Updated Nov 5, 2024 • 40
OpenVINO/Phi-3-medium-4k-instruct-int4-ov

Text Generation • Updated Oct 29, 2024 • 74 • 3
OpenVINO/Phi-3-medium-4k-instruct-int8-ov

Text Generation • Updated Nov 5, 2024 • 23
OpenVINO/starcoder2-15b-int8-ov

Text Generation • Updated Nov 5, 2024 • 80
OpenVINO/starcoder2-15b-int4-ov

Text Generation • Updated Nov 5, 2024 • 97 • 2
OpenVINO/starcoder2-15b-fp16-ov

Text Generation • Updated Nov 5, 2024 • 87
OpenVINO/starcoder2-7b-fp16-ov

Text Generation • Updated Nov 5, 2024 • 95
OpenVINO/starcoder2-7b-int4-ov

Text Generation • Updated Nov 5, 2024 • 83 • 1
OpenVINO/starcoder2-7b-int8-ov

Text Generation • Updated Nov 5, 2024 • 78
OpenVINO/Phi-3-mini-4k-instruct-fp16-ov

Text Generation • Updated Nov 25, 2024 • 38 • 3
OpenVINO/Phi-3-mini-128k-instruct-fp16-ov

Text Generation • Updated Nov 5, 2024 • 34
OpenVINO/Phi-3-mini-128k-instruct-int4-ov

Text Generation • Updated Oct 31, 2024 • 75 • 3
OpenVINO/Phi-3-mini-4k-instruct-int4-ov

Text Generation • Updated Nov 25, 2024 • 1.4k • 4
OpenVINO/Phi-3-mini-4k-instruct-int8-ov

Text Generation • Updated Nov 5, 2024 • 27
OpenVINO/Phi-3-mini-128k-instruct-int8-ov

Text Generation • Updated Nov 5, 2024 • 28 • 5
OpenVINO/RedPajama-INCITE-Instruct-3B-v1-fp16-ov

Updated Jul 29, 2025 • 21
OpenVINO/RedPajama-INCITE-Instruct-3B-v1-int4-ov

Updated Jul 29, 2025 • 24 • 1
OpenVINO/RedPajama-INCITE-Instruct-3B-v1-int8-ov

Updated Jul 29, 2025 • 22
OpenVINO/gemma-2b-it-fp16-ov

Updated Nov 20, 2024 • 17
OpenVINO/gemma-2b-it-int8-ov

Updated Nov 25, 2024 • 19
OpenVINO/gemma-2b-it-int4-ov

Updated Nov 25, 2024 • 56
OpenVINO/gemma-7b-fp16-ov

Updated Nov 5, 2024 • 16
OpenVINO/gemma-7b-int4-ov

Updated Nov 5, 2024 • 43 • 1
OpenVINO/gemma-7b-int8-ov

Updated Nov 5, 2024 • 40
OpenVINO/gemma-7b-it-int8-ov

Updated Nov 5, 2024 • 16
OpenVINO/gemma-7b-it-fp16-ov

Updated Nov 5, 2024 • 21
OpenVINO/gemma-7b-it-int4-ov

Updated Nov 5, 2024 • 33
OpenVINO/codegen-6B-multi-int4-ov

Updated Nov 5, 2024 • 42
OpenVINO/codegen-6B-multi-fp16-ov

Updated Nov 5, 2024 • 41
OpenVINO/codegen-6B-multi-int8-ov

Updated Nov 5, 2024 • 47
OpenVINO/Phi-3.5-mini-instruct-fp16-ov

Updated Nov 25, 2024 • 20
OpenVINO/Phi-3.5-mini-instruct-int8-ov

Updated Nov 25, 2024 • 71
OpenVINO/Phi-3.5-mini-instruct-int4-ov

Updated Nov 25, 2024 • 528 • 10
OpenVINO/gemma-2-9b-it-int4-ov

Updated Nov 25, 2024 • 95
OpenVINO/gemma-2-9b-it-int8-ov

Updated Nov 25, 2024 • 17
OpenVINO/gemma-2-9b-it-fp16-ov

Updated Nov 25, 2024 • 33
OpenVINO/DeepSeek-R1-Distill-Qwen-1.5B-fp16-ov

Updated Mar 20, 2025 • 31
OpenVINO/DeepSeek-R1-Distill-Qwen-1.5B-int8-ov

Updated Mar 20, 2025 • 42
OpenVINO/DeepSeek-R1-Distill-Qwen-1.5B-int4-ov

Updated Mar 20, 2025 • 826 • 2
OpenVINO/DeepSeek-R1-Distill-Qwen-7B-int4-ov

Updated Mar 24, 2025 • 521 • 2
OpenVINO/DeepSeek-R1-Distill-Qwen-7B-int8-ov

Updated Mar 24, 2025 • 31
OpenVINO/DeepSeek-R1-Distill-Qwen-7B-fp16-ov

Updated Mar 24, 2025 • 22
OpenVINO/DeepSeek-R1-Distill-Qwen-14B-fp16-ov

Updated Mar 31, 2025 • 36 • 1
OpenVINO/DeepSeek-R1-Distill-Qwen-14B-int8-ov

Updated Mar 31, 2025 • 27 • 1
OpenVINO/DeepSeek-R1-Distill-Qwen-14B-int4-ov

Updated Mar 31, 2025 • 221 • 1
OpenVINO/Qwen2.5-1.5B-Instruct-fp16-ov

Updated Apr 28, 2025 • 166 • 1
OpenVINO/Qwen2.5-1.5B-Instruct-int4-ov

Updated Apr 28, 2025 • 1.62k • 2
OpenVINO/Qwen2.5-1.5B-Instruct-int8-ov

Updated Apr 28, 2025 • 219
OpenVINO/Qwen2.5-14B-Instruct-int4-ov

Updated Apr 28, 2025 • 222 • 1
OpenVINO/Qwen2.5-14B-Instruct-int8-ov

Updated Apr 28, 2025 • 29
OpenVINO/Qwen2.5-14B-Instruct-fp16-ov

Updated Apr 28, 2025 • 23 • 1
OpenVINO/Qwen2.5-7B-Instruct-fp16-ov

Updated Apr 28, 2025 • 40
OpenVINO/Qwen2.5-7B-Instruct-int8-ov

Updated Apr 28, 2025 • 68
OpenVINO/Qwen2.5-7B-Instruct-int4-ov

Updated Apr 28, 2025 • 1.68k • 4
OpenVINO/Phi-4-mini-instruct-int4-ov

Text Generation • Updated Jul 6 • 1.01k • 6
OpenVINO/Phi-4-mini-instruct-int8-ov

Text Generation • Updated Apr 16, 2025 • 248
OpenVINO/Phi-4-mini-instruct-fp16-ov

Text Generation • Updated Apr 16, 2025 • 32
OpenVINO/Qwen2-0.5B-Instruct-fp16-ov

Updated Apr 24, 2025 • 18
OpenVINO/Qwen2-0.5B-Instruct-int8-ov

Updated Apr 24, 2025 • 13
OpenVINO/Qwen2-0.5B-Instruct-int4-ov

Updated Apr 24, 2025 • 331 • 1
OpenVINO/Qwen2-0.5B-int8-ov

Updated Apr 24, 2025 • 20 • 1
OpenVINO/Qwen2-0.5B-fp16-ov

Updated Apr 24, 2025 • 13
OpenVINO/Qwen2-0.5B-int4-ov

Updated Apr 24, 2025 • 24
OpenVINO/Qwen2-1.5B-fp16-ov

Updated Apr 24, 2025 • 15
OpenVINO/Qwen2-1.5B-int8-ov

Updated Apr 24, 2025 • 14
OpenVINO/Qwen2-1.5B-int4-ov

Updated Apr 24, 2025 • 15
OpenVINO/Qwen2-1.5B-Instruct-fp16-ov

Updated Apr 24, 2025 • 11
OpenVINO/Qwen2-1.5B-Instruct-int8-ov

Updated Apr 24, 2025 • 17
OpenVINO/Qwen2-7B-Instruct-fp16-ov

Updated Apr 24, 2025 • 17
OpenVINO/Qwen2-7B-Instruct-int4-ov

Updated Apr 24, 2025 • 15
OpenVINO/Qwen2-1.5B-Instruct-int4-ov

Updated Apr 24, 2025 • 21
OpenVINO/Qwen2-7B-Instruct-int8-ov

Updated Apr 24, 2025 • 18
OpenVINO/Qwen3-0.6B-int4-ov

Updated Apr 30, 2025 • 2.02k • 3
OpenVINO/Qwen3-0.6B-fp16-ov

Updated Apr 30, 2025 • 78 • 1
OpenVINO/Qwen3-0.6B-int8-ov

Updated Apr 30, 2025 • 102
OpenVINO/Qwen3-1.7B-fp16-ov

Updated Apr 30, 2025 • 23
OpenVINO/Qwen3-1.7B-int8-ov

Updated Apr 30, 2025 • 99 • 1
OpenVINO/Qwen3-1.7B-int4-ov

Updated Apr 30, 2025 • 1.41k • 2
OpenVINO/Qwen3-4B-fp16-ov

Updated Apr 30, 2025 • 30 • 1
OpenVINO/Qwen3-4B-int8-ov

Updated Feb 24 • 328 • 1
OpenVINO/Qwen3-4B-int4-ov

Updated Feb 24 • 1.46k • 2
OpenVINO/Qwen3-8B-fp16-ov

Updated Apr 30, 2025 • 33 • 1
OpenVINO/Qwen3-8B-int8-ov

Updated Feb 24 • 574
OpenVINO/Qwen3-8B-int4-ov

Updated Feb 24 • 1.53k • 11
OpenVINO/Qwen3-14B-int8-ov

Updated Apr 30, 2025 • 31
OpenVINO/Qwen3-14B-fp16-ov

Updated Apr 30, 2025 • 31
OpenVINO/Qwen3-14B-int4-ov

Text Generation • Updated Jun 11 • 422 • 1
OpenVINO/phi-4-fp16-ov

Text Generation • Updated May 23, 2025 • 36
OpenVINO/phi-4-int8-ov

Text Generation • Updated May 23, 2025 • 31
OpenVINO/phi-4-int4-ov

Text Generation • Updated May 26, 2025 • 69 • 3
LLMs optimized for NPU

Collection

10 items • Updated 5 days ago • 52
OpenVINO/Qwen3-30B-A3B-Instruct-2507-int8-ov

Text Generation • Updated Feb 27 • 40
OpenVINO/Qwen3-30B-A3B-Instruct-2507-int4-ov

Text Generation • Updated Apr 7 • 310 • 4
OpenVINO/Qwen3-Coder-30B-A3B-Instruct-int4-ov

Text Generation • Updated Apr 7 • 600 • 3
OpenVINO/Qwen3-Coder-30B-A3B-Instruct-int8-ov

Text Generation • Updated Feb 26 • 52 • 1
OpenVINO/gpt-oss-20b-int4-ov

Text Generation • Updated Apr 7 • 623 • 6
OpenVINO/gpt-oss-20b-int8-ov

Text Generation • Updated Feb 25 • 65 • 1
OpenVINO/LFM2.5-350M-int8-ov

Text Generation • Updated Aug 26 • 149 • 5
OpenVINO/LFM2.5-350M-fp16-ov

Text Generation • Updated Aug 26 • 56 • 4
OpenVINO/LFM2-24B-A2B-int4-ov

Text Generation • Updated May 8 • 78 • 2
OpenVINO/LFM2.5-8B-A1B-int4-ov

Text Generation • Updated Aug 3 • 1.04k • 1

Upvote

Collection guide
Browse collections