MODEL CATALOG / INTEL
A structured reference for models prepared for Intel hardware. Add or replace catalog groups from your JSON without changing the page layout.
Models
219
RUNTIME
OPENVINO
HARDWARE TARGETS
CPU ยท GPU ยท NPU
Model HQ Catalog
Intel Models
CPU Models
GGUF and tool models that run on the CPU alone โ no GPU or NPU required.
| Category | Model | Parameters | Format |
|---|---|---|---|
| Agentic | slim-extract-phi-3-gguf | 3.8 | GGUF |
| Agentic | slim-extract-qwen-1.5b-gguf | 1.5 | GGUF |
| Agentic | slim-extract-qwen-nano-gguf | 0.5 | GGUF |
| Agentic | slim-summary-phi-3-gguf | 1.1 | GGUF |
| Agentic | slim-xsum-phi-3-gguf | 3.8 | GGUF |
| Agentic | slim-boolean-phi-3-gguf | 3.8 | GGUF |
| Agentic | slim-sa-ner-phi-3-gguf | 3.8 | GGUF |
| Agentic | slim-q-gen-phi-3-tool | 3.8 | Tool |
| Agentic | slim-qa-gen-phi-3-tool | 3.8 | Tool |
| Agentic | slim-ner-tool | 1.1 | Tool |
| Agentic | slim-sentiment-tool | 1.1 | Tool |
| Agentic | slim-emotions-tool | 1.1 | Tool |
| Agentic | slim-ratings-tool | 1.1 | Tool |
| Agentic | slim-intent-tool | 1.1 | Tool |
| Agentic | slim-nli-tool | 1.1 | Tool |
| Agentic | slim-topics-tool | 1.1 | Tool |
| Agentic | slim-tags-tool | 1.1 | Tool |
| Agentic | slim-sql-tool | 1.1 | Tool |
| Agentic | slim-category-tool | 1.1 | Tool |
| Agentic | slim-xsum-tool | 1.1 | Tool |
| Agentic | slim-extract-tool | 2.8 | Tool |
| Agentic | slim-extract-tiny-tool | 1.1 | Tool |
| Agentic | slim-summary-tiny-tool | 1.1 | Tool |
| Agentic | slim-boolean-tool | 2.8 | Tool |
| Agentic | slim-sa-ner-tool | 2.8 | Tool |
| Agentic | slim-tags-3b-tool | 2.8 | Tool |
| Agentic | slim-summary-tool | 2.8 | Tool |
| Agentic | slim-q-gen-tiny-tool | 1.1 | Tool |
| Agentic | slim-qa-gen-tiny-tool | 1.1 | Tool |
| Coding | qwen-2.5-7b-coder-gguf | 7 | GGUF |
| General Chat | qwen3-1.7b-gguf | 1.7 | GGUF |
| General Chat | qwen3-8b-gguf | 8 | GGUF |
| General Chat | qwen3-14b-gguf | 14 | GGUF |
| General Chat | qwen2.5-32b-gguf | 32 | GGUF |
| General Chat | deepseek-qwen-14b-gguf | 14 | GGUF |
| General Chat | deepseek-qwen-7b-gguf | 7 | GGUF |
| General Chat | dragon-llama-3.1-gguf | 8 | GGUF |
| General Chat | phi-3-gguf | 3.8 | GGUF |
| General Chat | phi-3.5-gguf | 3.8 | GGUF |
| General Chat | phi-4-gguf | 14 | GGUF |
| General Chat | phi-4-mini-gguf | 4 | GGUF |
| General Chat | phi-4-mini-reasoning-gguf | 4 | GGUF |
| General Chat | mistral-3.2-24b-gguf | 24 | GGUF |
| General Chat | openhermes-2.5-mistral-7b-gguf | 7.3 | GGUF |
| General Chat | zephyr-7b-beta-gguf | 7.3 | GGUF |
| General Chat | starling-lm-7b-alpha-gguf | 7 | GGUF |
| General Chat | gemma-3-4b-gguf | 4 | GGUF |
| General Chat | gemma-3-12b-gguf | 12 | GGUF |
| Instruct | qwen2-7B-instruct-gguf | 7 | GGUF |
| Instruct | qwen3-4b-instruct-gguf | 4 | GGUF |
| Instruct | qwen2-1.5b-instruct-gguf | 1.5 | GGUF |
| Instruct | qwen2-0.5b-instruct-gguf | 0.5 | GGUF |
| Instruct | qwen-2.5-14b-instruct-gguf | 14 | GGUF |
| Instruct | mistral-7b-instruct-v0.3-gguf | 7.3 | GGUF |
| Instruct | gemma-2-9b-instruct-gguf | 9 | GGUF |
| Instruct | gemma-2-27b-instruct-gguf | 27 | GGUF |
| Question-answer | bling-qwen-0.5b-gguf | 0.5 | GGUF |
| Question-answer | dragon-qwen-7b-gguf | 7 | GGUF |
| Question-answer | bling-phi-3-gguf | 3.8 | GGUF |
| Question-answer | bling-phi-3.5-gguf | 3.8 | GGUF |
| Question-answer | dragon-mistral-0.3-gguf | 7.3 | GGUF |
| Question-answer | dragon-yi-9b-gguf | 8.8 | GGUF |
| Question-answer | bling-stablelm-3b-gguf | 2.8 | GGUF |
| Question-answer | bling-qwen-mini-tool | 1.5 | Tool |
| Question-answer | bling-answer-tool | 1.1 | Tool |
| Question-answer | dragon-mistral-answer-tool | 7.3 | Tool |
| Question-answer | dragon-yi-answer-tool | 5.8 | Tool |
| Question-answer | dragon-llama-answer-tool | 7 | Tool |
| Question-answer | bling-tiny-llama-onnx | 1.1 | ONNX |
| Question-answer | bling-phi-3-onnx | 3.8 | ONNX |
| Question-answer | bling-phi-3-ov | 3.8 | OpenVINO |
| Question-answer | bling-qwen-500m-ov | 0.5 | OpenVINO |
| Question-answer | bling-qwen-1.5b-ov | 1.5 | OpenVINO |
| Question-answer | bling-tiny-llama-ov | 1.1 | OpenVINO |
GPU/CPU/NPU Models
OpenVINO (OV) and ONNX models that run on the available GPU, CPU, or NPU.
| Category | Model | Parameters | Format |
|---|---|---|---|
| Agentic | slim-sentiment-onnx | 1.1 | ONNX |
| Agentic | slim-extract-tiny-onnx | 1.1 | ONNX |
| Agentic | slim-summary-tiny-onnx | 1.1 | ONNX |
| Agentic | slim-sql-onnx | 1.1 | ONNX |
| Agentic | slim-emotions-onnx | 1.1 | ONNX |
| Agentic | slim-topics-onnx | 1.1 | ONNX |
| Agentic | slim-ner-onnx | 1.1 | ONNX |
| Agentic | slim-intent-onnx | 1.1 | ONNX |
| Agentic | slim-tags-onnx | 1.1 | ONNX |
| Agentic | slim-ratings-onnx | 1.1 | ONNX |
| Agentic | slim-summary-phi-3-onnx | 3.8 | ONNX |
| Agentic | slim-extract-phi-3-onnx | 3.8 | ONNX |
| Agentic | slim-boolean-phi-3-onnx | 3.8 | ONNX |
| Agentic | slim-sentiment-ov | 1.1 | OpenVINO |
| Agentic | slim-xsum-phi-3-ov | 3.8 | OpenVINO |
| Agentic | slim-boolean-phi-3-ov | 3.8 | OpenVINO |
| Agentic | slim-sa-ner-phi-3-ov | 3.8 | OpenVINO |
| Agentic | slim-summary-phi-3-ov | 3.8 | OpenVINO |
| Agentic | slim-sql-qwen-base-ov | 2 | OpenVINO |
| Agentic | slim-sql-phi-3-ov | 3.8 | OpenVINO |
| Agentic | slim-extract-phi-3-ov | 3.8 | OpenVINO |
| Agentic | slim-extract-tiny-ov | 1.1 | OpenVINO |
| Agentic | slim-extract-qwen-0.5b-ov | 0.5 | OpenVINO |
| Agentic | slim-extract-qwen-1.5b-ov | 1.5 | OpenVINO |
| Agentic | slim-summary-tiny-ov | 1.1 | OpenVINO |
| Agentic | slim-sql-ov | 1.1 | OpenVINO |
| Agentic | slim-emotions-ov | 1.1 | OpenVINO |
| Agentic | slim-topics-ov | 1.1 | OpenVINO |
| Agentic | slim-ner-ov | 1.1 | OpenVINO |
| Agentic | slim-intent-ov | 1.1 | OpenVINO |
| Agentic | slim-category-ov | 1.1 | OpenVINO |
| Agentic | slim-tags-ov | 1.1 | OpenVINO |
| Agentic | slim-ratings-ov | 1.1 | OpenVINO |
| Agentic | slim-q-gen-tiny-ov | 1.1 | OpenVINO |
| Agentic | slim-qa-gen-tiny-ov | 1.1 | OpenVINO |
| Coding | qwen2.5-coder-7b-instruct-ov | 7 | OpenVINO |
| Coding | codegemma-7b-it-ov | 7 | OpenVINO |
| Embedding | industry-bert-contracts-ov | NA | OpenVINO |
| Embedding | industry-bert-insurance-ov | NA | OpenVINO |
| Embedding | industry-bert-asset-management-ov | NA | OpenVINO |
| Embedding | industry-bert-sec-ov | NA | OpenVINO |
| Embedding | industry-bert-loans-ov | NA | OpenVINO |
| Embedding | all-mini-lm-l6-v2-ov | NA | OpenVINO |
| Embedding | all-mpnet-base-v2-ov | NA | OpenVINO |
| Embedding | paraphrase-multilingual-MiniLM-L12-v2-ov | NA | OpenVINO |
| Embedding | gte-small-ov | NA | OpenVINO |
| Embedding | gte-base-ov | NA | OpenVINO |
| Embedding | gte-large-ov | NA | OpenVINO |
| Embedding | bge-small-en-v1.5-ov | NA | OpenVINO |
| Embedding | bge-base-en-v1.5-ov | NA | OpenVINO |
| Embedding | bge-large-en-v1.5-ov | NA | OpenVINO |
| General Chat | llama-2-chat-onnx | 7 | ONNX |
| General Chat | qwen2-0.5b-chat-ov | 0.5 | OpenVINO |
| General Chat | phi-3-ov | 3.8 | OpenVINO |
| General Chat | phi-4-ov | 14 | OpenVINO |
| General Chat | phi-4-mini-ov | 4 | OpenVINO |
| General Chat | qwen3-8b-ov | 8 | OpenVINO |
| General Chat | qwen3-1.7b-ov | 1.7 | OpenVINO |
| General Chat | qwen3-4b-ov | 4 | OpenVINO |
| General Chat | qwen3-14b-ov | 14 | OpenVINO |
| General Chat | llama-2-chat-ov | 7 | OpenVINO |
| General Chat | llama-2-13b-chat-ov | 13 | OpenVINO |
| General Chat | tiny-llama-chat-ov | 1.1 | OpenVINO |
| General Chat | dolphin-2.9.3-mistral-7b-32k-ov | 7.3 | OpenVINO |
| General Chat | dolphin-2.9.4-llama3.1-8b-ov | 8 | OpenVINO |
| General Chat | zephyr-mistral-7b-chat-ov | 7.3 | OpenVINO |
| General Chat | teknium-open-hermes-2.5-mistral-ov | 7.3 | OpenVINO |
| General Chat | yi-9b-chat-ov | 8.8 | OpenVINO |
| General Chat | yi-6b-1.5v-chat-ov | 5.8 | OpenVINO |
| General Chat | stablelm-zephyr-3b-ov | 2.8 | OpenVINO |
| General Chat | stablelm-2-zephyr-1_6b-ov | 1.6 | OpenVINO |
| General Chat | stablelm-2-12b-chat-ov | 12 | OpenVINO |
| General Chat | intel-neural-chat-7b-v3-2-ov | 7 | OpenVINO |
| General Chat | tiny-dolphin-2.8-1.1b-ov | 1.1 | OpenVINO |
| General Chat | dreamgen-wizardlm-2-7b-ov | 7 | OpenVINO |
| General Chat | openchat-3.6-8b-20240522-ov | 8 | OpenVINO |
| General Chat | lcm-dreamshaper-ov | NA | OpenVINO |
| Instruct | llama-3.1-instruct-onnx | 8 | ONNX |
| Instruct | llama-3.2-1b-instruct-onnx | 1.3 | ONNX |
| Instruct | llama-3.2-3b-instruct-onnx | 3 | ONNX |
| Instruct | phi-3-onnx | 3.8 | ONNX |
| Instruct | mistral-7b-instruct-v0.3-onnx | 7.3 | ONNX |
| Instruct | gemma-2b-it-onnx | 2 | ONNX |
| Instruct | qwen2-vl-2b-instruct-ov | 2 | OpenVINO |
| Instruct | qwen2-vl-7b-instruct-ov | 7 | OpenVINO |
| Instruct | qwen2-7b-instruct-ov | 7 | OpenVINO |
| Instruct | qwen2-1.5b-instruct-ov | 1.5 | OpenVINO |
| Instruct | qwen2.5-1.5b-instruct-ov | 1.5 | OpenVINO |
| Instruct | qwen2.5-0.5b-instruct-ov | 0.5 | OpenVINO |
| Instruct | qwen2.5-3b-instruct-ov | 3 | OpenVINO |
| Instruct | qwen2.5-14b-instruct-ov | 14 | OpenVINO |
| Instruct | qwen2.5-32b-instruct-ov | 32 | OpenVINO |
| Instruct | qwen2.5-72b-instruct-ov | 72 | OpenVINO |
| Instruct | llama-3.1-instruct-ov | 8 | OpenVINO |
| Instruct | llama-3.2-3b-instruct-ov | 3 | OpenVINO |
| Instruct | llama-3.2-1b-instruct-ov | 1.1 | OpenVINO |
| Instruct | mistral-7b-instruct-v0.3-ov | 7.3 | OpenVINO |
| Instruct | mistral-small-instruct-2409-ov | 22 | OpenVINO |
| Instruct | mistral-nemo-instruct-2407-ov | 12 | OpenVINO |
| Instruct | mistral-7b-instruct-v0.2-ov | 7.3 | OpenVINO |
| Instruct | gemma-7b-it-ov | 7 | OpenVINO |
| Instruct | gemma-2b-it-ov | 2 | OpenVINO |
| Math | mathstral-7b-ov | 7.3 | OpenVINO |
| Prompt Safety | protectai-prompt-injection-onnx | NA | ONNX |
| Prompt Safety | valurank-bias-onnx | NA | ONNX |
| Prompt Safety | unitary-toxic-roberta-onnx | NA | ONNX |
| Prompt Safety | protectai-prompt-injection-ov | NA | OpenVINO |
| Prompt Safety | malicious-url-detector-ov | NA | OpenVINO |
| Prompt Safety | xlm-roberta-language-detector-ov | NA | OpenVINO |
| Prompt Safety | valurank-bias-ov | NA | OpenVINO |
| Prompt Safety | unitary-toxic-roberta-ov | NA | OpenVINO |
| Question-answer | dragon-mistral-0.3-onnx | 7.3 | ONNX |
| Question-answer | dragon-qwen-7b-ov | 7 | OpenVINO |
| Question-answer | dragon-llama2-ov | 7 | OpenVINO |
| Question-answer | nvidia-llama3-chatqa-1.5-8b-ov | 8 | OpenVINO |
| Question-answer | dragon-mistral-ov | 7.3 | OpenVINO |
| Question-answer | dragon-mistral-0.3-ov | 7.3 | OpenVINO |
| Re-ranker | jina-reranker-tiny-onnx | NA | ONNX |
| Re-ranker | jina-reranker-turbo-onnx | NA | ONNX |
| Re-ranker | jina-reranker-v1-tiny-en-ov | NA | OpenVINO |
| Re-ranker | jina-reranker-v1-turbo-en-ov | NA | OpenVINO |
| Text-to-speech | speech-t5-tts-ov | NA | OpenVINO |
| Vision | phi-3-vision-onnx | 3.8 | ONNX |
| Vision | llama-11b-vision-instruct-ov | 11 | OpenVINO |
NPU Models
Models designed to run on Neural Processing Units for efficient, low-power inference.
| Category | Model | Parameters | Format |
|---|---|---|---|
| NPU Models | bling-tiny-llama-npu-ov | 1.1 | OpenVINO |
| NPU Models | llama-3.1-8b-instruct-npu-ov | 8 | OpenVINO |
| NPU Models | llama-3.2-3b-instruct-npu-ov | 3 | OpenVINO |
| NPU Models | llama-3.2-1b-instruct-npu-ov | 1.1 | OpenVINO |
| NPU Models | phi-3-npu-ov | 3.8 | OpenVINO |
| NPU Models | phi-4-mini-npu-ov | 4 | OpenVINO |
| NPU Models | phi-4-npu-ov | 14 | OpenVINO |
| NPU Models | mistral-7b-v0.3-npu-ov | 7.3 | OpenVINO |
| NPU Models | yi-9b-npu-ov | 8.8 | OpenVINO |
| NPU Models | slim-sentiment-npu-ov | 1.1 | OpenVINO |
| NPU Models | slim-extract-tiny-npu-ov | 1.1 | OpenVINO |
| NPU Models | slim-summary-tiny-npu-ov | 1.1 | OpenVINO |
| NPU Models | slim-sql-npu-ov | 1.1 | OpenVINO |
| NPU Models | slim-emotions-npu-ov | 1.1 | OpenVINO |
| NPU Models | slim-topics-npu-ov | 1.1 | OpenVINO |
| NPU Models | slim-ner-npu-ov | 1.1 | OpenVINO |
| NPU Models | slim-intent-npu-ov | 1.1 | OpenVINO |
| NPU Models | slim-tags-npu-ov | 1.1 | OpenVINO |
| NPU Models | slim-ratings-npu-ov | 1.1 | OpenVINO |
| NPU Models | llama-3.2-3b-onnx-qnn | 3 | QNN |
| NPU Models | phi-3.5-onnx-qnn | NA | QNN |
