MODEL CATALOG / AMD
A structured reference for models prepared for AMD hardware. Add or replace catalog groups from your JSON without changing the page layout.
MODELS
325
RUNTIME
ONNX
HARDWARE TARGETS
CPU · GPU · NPU
Model HQ Catalog
AMD Models
CPU Models
GGUF and tool models that run on the CPU alone — no GPU or NPU required.
| Category | Model | Parameters | Format |
|---|---|---|---|
| Agentic | slim-boolean-phi-3-gguf | 3.8 | GGUF |
| 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-sa-ner-phi-3-gguf | 3.8 | GGUF |
| Agentic | slim-summary-phi-3-gguf | 3.8 | GGUF |
| Agentic | slim-xsum-phi-3-gguf | 3.8 | GGUF |
| Agentic | slim-boolean-tool | 1.1 | Tool |
| Agentic | slim-category-tool | 1.1 | Tool |
| Agentic | slim-emotions-tool | 1.1 | Tool |
| Agentic | slim-extract-tool | 1.1 | Tool |
| Agentic | slim-intent-tool | 1.1 | Tool |
| Agentic | slim-ner-tool | 1.1 | Tool |
| Agentic | slim-nli-tool | 1.1 | Tool |
| Agentic | slim-q-gen-phi-3-tool | 3.8 | Tool |
| Agentic | slim-q-gen-tiny-tool | 1.1 | Tool |
| Agentic | slim-qa-gen-phi-3-tool | 3.8 | Tool |
| Agentic | slim-qa-gen-tiny-tool | 1.1 | Tool |
| Agentic | slim-ratings-tool | 1.1 | Tool |
| Agentic | slim-sa-ner-tool | 1.1 | Tool |
| Agentic | slim-sentiment-tool | 1.1 | Tool |
| Agentic | slim-sql-tool | 1.1 | Tool |
| Agentic | slim-summary-tiny-tool | 1.1 | Tool |
| Agentic | slim-summary-tool | 1.1 | Tool |
| Agentic | slim-tags-3b-tool | 3 | Tool |
| Agentic | slim-tags-tool | 1.1 | Tool |
| Agentic | slim-topics-tool | 1.1 | Tool |
| Agentic | slim-xsum-tool | 1.1 | Tool |
| Coding | qwen2.5-coder-0.5b-instruct-generic-cpu:4-foundry | 0.5 | NA |
| Coding | qwen2.5-coder-1.5b-instruct-generic-cpu:4-foundry | 1.5 | NA |
| Coding | qwen2.5-coder-14b-instruct-generic-cpu:4-foundry | 14 | NA |
| Coding | qwen2.5-coder-7b-instruct-generic-cpu:4-foundry | 7 | NA |
| Coding | qwen-2.5-7b-coder-gguf | 7 | GGUF |
| General Chat | gpt-oss-20b-generic-cpu:1-foundry | NA | Cloud |
| General Chat | deepseek-r1-distill-qwen-14b-generic-cpu:4-foundry | 14 | NA |
| General Chat | deepseek-r1-distill-qwen-7b-generic-cpu:4-foundry | 7 | NA |
| General Chat | qwen3-0.6b-generic-cpu:4-foundry | 0.6 | NA |
| General Chat | qwen3-1.7b-generic-cpu:2-foundry | 1.7 | NA |
| General Chat | qwen3-14b-generic-cpu:2-foundry | 14 | NA |
| General Chat | qwen3-4b-generic-cpu:3-foundry | 4 | NA |
| General Chat | qwen3-8b-generic-cpu:2-foundry | 8 | NA |
| General Chat | Phi-4-mini-reasoning-generic-cpu:3-foundry | 3.8 | NA |
| General Chat | Phi-4-generic-cpu:2-foundry | 14 | NA |
| General Chat | qwen3.5-0.8b-generic-cpu:2-foundry | 0.8 | NA |
| General Chat | qwen3.5-2b-generic-cpu:2-foundry | 2 | NA |
| General Chat | qwen3.5-4b-generic-cpu:2-foundry | 4 | NA |
| General Chat | qwen3.5-9b-generic-cpu:2-foundry | 9 | NA |
| General Chat - GGUF | deepseek-qwen-14b-gguf | 14 | GGUF |
| General Chat - GGUF | deepseek-qwen-7b-gguf | 7 | GGUF |
| General Chat - GGUF | dragon-llama-3.1-gguf | 8 | GGUF |
| General Chat - GGUF | gemma-3-12b-gguf | 12 | GGUF |
| General Chat - GGUF | gemma-3-4b-gguf | 4 | GGUF |
| General Chat - GGUF | gemma-4-26b-gguf | 26 | GGUF |
| General Chat - GGUF | gemma-4-2b-gguf | 2 | GGUF |
| General Chat - GGUF | gemma-4-4b-gguf | 4 | GGUF |
| General Chat - GGUF | gpt-oss-20b-gguf | 20 | GGUF |
| General Chat - GGUF | granite-4-micro-gguf | 1.1 | GGUF |
| General Chat - GGUF | llama-2-7b-chat-gguf | 7 | GGUF |
| General Chat - GGUF | liquidai-lfm2-2.6b-gguf | 2.6 | GGUF |
| General Chat - GGUF | ministral-3-14b-gguf | 14 | GGUF |
| General Chat - GGUF | minicpm-2.6-gguf | 4 | GGUF |
| General Chat - GGUF | mistral-small-3.2-24b-gguf | 24 | GGUF |
| General Chat - GGUF | olmo-13b-gguf | 13 | GGUF |
| General Chat - GGUF | openhermes-2.5-mistral-7b-gguf | 7 | GGUF |
| General Chat - GGUF | phi-3-gguf | 3.8 | GGUF |
| General Chat - GGUF | phi-3.5-gguf | 3.8 | GGUF |
| General Chat - GGUF | phi-4-gguf | 14 | GGUF |
| General Chat - GGUF | phi-4-mini-gguf | 3.8 | GGUF |
| General Chat - GGUF | phi-4-mini-reasoning-gguf | 3.8 | GGUF |
| General Chat - GGUF | qwen-3.5-27b-gguf | 27 | GGUF |
| General Chat - GGUF | qwen-3.5-35b-a3b-gguf | 35 | GGUF |
| General Chat - GGUF | qwen-3.5-4b-gguf | 4 | GGUF |
| General Chat - GGUF | qwen-3.5-9b-gguf | 9 | GGUF |
| General Chat - GGUF | qwen2.5-32b-gguf | 32 | GGUF |
| General Chat - GGUF | qwen2.5-72b-gguf | 72 | GGUF |
| General Chat - GGUF | qwen3-1.7b-gguf | 1.7 | GGUF |
| General Chat - GGUF | qwen3-14b-gguf | 14 | GGUF |
| General Chat - GGUF | qwen3-8b-gguf | 8 | GGUF |
| General Chat - GGUF | starling-lm-7b-alpha-gguf | 7 | GGUF |
| General Chat - GGUF | tiny-llama-chat-gguf | 1.1 | GGUF |
| General Chat - GGUF | zephyr-7b-beta-gguf | 7 | GGUF |
| Instruct | qwen2.5-0.5b-instruct-generic-cpu:4-foundry | 0.5 | NA |
| Instruct | qwen2.5-1.5b-instruct-generic-cpu:4-foundry | 1.5 | NA |
| Instruct | qwen2.5-14b-instruct-generic-cpu:4-foundry | 14 | NA |
| Instruct | qwen2.5-7b-instruct-generic-cpu:4-foundry | 7 | NA |
| Instruct | Phi-4-mini-instruct-generic-cpu:5-foundry | 3.8 | NA |
| Instruct | mistralai-Mistral-7B-Instruct-v0-2-generic-cpu:3-foundry | 7 | NA |
| Instruct | Phi-3-mini-128k-instruct-generic-cpu:3-foundry | 3.8 | NA |
| Instruct | Phi-3-mini-4k-instruct-generic-cpu:3-foundry | 3.8 | NA |
| Instruct | Phi-3.5-mini-instruct-generic-cpu:2-foundry | 3.8 | NA |
| Instruct - GGUF | gemma-2-27b-instruct-gguf | 27 | GGUF |
| Instruct - GGUF | gemma-2-9b-instruct-gguf | 9 | GGUF |
| Instruct - GGUF | llama-3-8b-instruct-gguf | 8 | GGUF |
| Instruct - GGUF | llama-3.1-instruct-gguf | 8 | GGUF |
| Instruct - GGUF | llama-3.2-1b-instruct-gguf | 1.1 | GGUF |
| Instruct - GGUF | llama-3.2-3b-instruct-gguf | 3 | GGUF |
| Instruct - GGUF | mistral-7b-instruct-v0.3-gguf | 7 | GGUF |
| Instruct - GGUF | qwen-2.5-14b-instruct-gguf | 14 | GGUF |
| Instruct - GGUF | qwen2-0.5b-instruct-gguf | 0.5 | GGUF |
| Instruct - GGUF | qwen2-1.5b-instruct-gguf | 1.5 | GGUF |
| Instruct - GGUF | qwen2-7B-instruct-gguf | 7 | GGUF |
| Instruct - GGUF | qwen3-4b-instruct-gguf | 4 | GGUF |
| Question-answer | bling-qwen-0.5b-gguf | 0.5 | GGUF |
| Question-answer | bling-tiny-llama-onnx | 1.1 | ONNX |
| Question-answer | bling-phi-3-onnx | 3.8 | ONNX |
| Question-answer | bling-qwen-1.5b-ov | 1.5 | OpenVINO |
| Question-answer | bling-tiny-llama-ov | 1.1 | OpenVINO |
| Question-answer | bling-phi-3-ov | 3.8 | OpenVINO |
| Question-answer | bling-qwen-mini-tool | 1.5 | Tool |
| Question-answer | dragon-qwen-7b-gguf | 7 | GGUF |
| Question-answer | dragon-mistral-0.3-gguf | 7 | GGUF |
| Question-answer | dragon-yi-9b-gguf | 9 | GGUF |
| Question-answer | dragon-llama-answer-tool | 7 | Tool |
| Question-answer | dragon-mistral-answer-tool | 7 | Tool |
| Question-answer | dragon-yi-answer-tool | 6 | Tool |
| Vision | qwen2.5-vl-3b-instruct-gguf | 3 | GGUF |
| Vision | qwen3-vl-30b-gguf | 30 | GGUF |
| Vision | qwen3-vl-4b-gguf | 4 | GGUF |
| Vision | qwen3-vl-8b-gguf | 8 | GGUF |
GPU/CPU/NPU Models
ONNX and OpenVINO (OV) models that run on the available GPU, CPU, or NPU.
| Category | Model | Parameters | Format |
|---|---|---|---|
| Agentic - ONNX | slim-boolean-phi-3-onnx | 3.8 | ONNX |
| Agentic - ONNX | slim-emotions-onnx | 1.1 | ONNX |
| Agentic - ONNX | slim-extract-phi-3-onnx | 3.8 | ONNX |
| Agentic - ONNX | slim-extract-tiny-onnx | 1.1 | ONNX |
| Agentic - ONNX | slim-intent-onnx | 1.1 | ONNX |
| Agentic - ONNX | slim-ner-onnx | 1.1 | ONNX |
| Agentic - ONNX | slim-ratings-onnx | 1.1 | ONNX |
| Agentic - ONNX | slim-sentiment-onnx | 1.1 | ONNX |
| Agentic - ONNX | slim-sql-onnx | 1.1 | ONNX |
| Agentic - ONNX | slim-summary-phi-3-onnx | 3.8 | ONNX |
| Agentic - ONNX | slim-summary-tiny-onnx | 1.1 | ONNX |
| Agentic - ONNX | slim-tags-onnx | 1.1 | ONNX |
| Agentic - ONNX | slim-topics-onnx | 1.1 | ONNX |
| Agentic - OV | slim-boolean-phi-3-ov | 3.8 | OpenVINO |
| Agentic - OV | slim-category-ov | 1.1 | OpenVINO |
| Agentic - OV | slim-emotions-ov | 1.1 | OpenVINO |
| Agentic - OV | slim-extract-phi-3-ov | 3.8 | OpenVINO |
| Agentic - OV | slim-extract-qwen-0.5b-ov | 0.5 | OpenVINO |
| Agentic - OV | slim-extract-qwen-1.5b-ov | 1.5 | OpenVINO |
| Agentic - OV | slim-extract-tiny-ov | 1.1 | OpenVINO |
| Agentic - OV | slim-intent-ov | 1.1 | OpenVINO |
| Agentic - OV | slim-ner-ov | 1.1 | OpenVINO |
| Agentic - OV | slim-q-gen-tiny-ov | 1.1 | OpenVINO |
| Agentic - OV | slim-qa-gen-tiny-ov | 1.1 | OpenVINO |
| Agentic - OV | slim-ratings-ov | 1.1 | OpenVINO |
| Agentic - OV | slim-sa-ner-phi-3-ov | 3.8 | OpenVINO |
| Agentic - OV | slim-sentiment-ov | 1.1 | OpenVINO |
| Agentic - OV | slim-sql-ov | 1.1 | OpenVINO |
| Agentic - OV | slim-sql-phi-3-ov | 3.8 | OpenVINO |
| Agentic - OV | slim-sql-qwen-base-ov | 1.5 | OpenVINO |
| Agentic - OV | slim-summary-phi-3-ov | 3.8 | OpenVINO |
| Agentic - OV | slim-summary-tiny-ov | 1.1 | OpenVINO |
| Agentic - OV | slim-tags-ov | 1.1 | OpenVINO |
| Agentic - OV | slim-topics-ov | 1.1 | OpenVINO |
| Agentic - OV | slim-xsum-phi-3-ov | 3.8 | OpenVINO |
| Coding | codegemma-7b-it-ov | 7 | OpenVINO |
| Coding | qwen2.5-coder-7b-instruct-ov | 7 | OpenVINO |
| Embedding - ONNX | all-mini-lm-l6-v2-onnx | 0.02 | ONNX |
| Embedding - ONNX | bge-base-en-v1.5-onnx | 0.11 | ONNX |
| Embedding - ONNX | bge-large-en-v1.5-onnx | 0.33 | ONNX |
| Embedding - ONNX | bge-small-en-v1.5-onnx | 0.03 | ONNX |
| Embedding - ONNX | gte-base-onnx | 0.11 | ONNX |
| Embedding - ONNX | gte-large-onnx | 0.33 | ONNX |
| Embedding - ONNX | gte-small-onnx | 0.03 | ONNX |
| Embedding - ONNX | industry-bert-contracts-onnx | 0.11 | ONNX |
| Embedding - ONNX | industry-bert-insurance-onnx | 0.11 | ONNX |
| Embedding - OV | all-mini-lm-l6-v2-ov | 0.02 | OpenVINO |
| Embedding - OV | all-mpnet-base-v2-ov | 0.11 | OpenVINO |
| Embedding - OV | bge-base-en-v1.5-ov | 0.11 | OpenVINO |
| Embedding - OV | bge-large-en-v1.5-ov | 0.33 | OpenVINO |
| Embedding - OV | bge-small-en-v1.5-ov | 0.03 | OpenVINO |
| Embedding - OV | gte-base-ov | 0.11 | OpenVINO |
| Embedding - OV | gte-large-ov | 0.33 | OpenVINO |
| Embedding - OV | gte-small-ov | 0.03 | OpenVINO |
| Embedding - OV | industry-bert-asset-management-ov | 0.11 | OpenVINO |
| Embedding - OV | industry-bert-contracts-ov | 0.11 | OpenVINO |
| Embedding - OV | industry-bert-insurance-ov | 0.11 | OpenVINO |
| Embedding - OV | industry-bert-loans-ov | 0.11 | OpenVINO |
| Embedding - OV | industry-bert-sec-ov | 0.11 | OpenVINO |
| Embedding - OV | paraphrase-multilingual-MiniLM-L12-v2-ov | 0.12 | OpenVINO |
| General Chat | gpt-oss-20b-generic-gpu:1-foundry | 20 | Cloud |
| General Chat | deepseek-r1-distill-qwen-14b-generic-gpu:4-foundry | 14 | NA |
| General Chat | qwen3-0.6b-generic-gpu:2-foundry | 0.6 | NA |
| General Chat | qwen3-1.7b-generic-gpu:2-foundry | 1.7 | NA |
| General Chat | qwen3-14b-generic-gpu:2-foundry | 14 | NA |
| General Chat | qwen3-4b-generic-gpu:2-foundry | 4 | NA |
| General Chat | qwen3-8b-generic-gpu:2-foundry | 8 | NA |
| General Chat | Phi-4-mini-reasoning-generic-gpu:3-foundry | 3.8 | NA |
| General Chat | deepseek-r1-distill-qwen-7b-generic-gpu:4-foundry | 7 | NA |
| General Chat | Phi-4-generic-gpu:2-foundry | 14 | NA |
| General Chat | qwen3.5-0.8b-generic-gpu:2-foundry | 0.8 | NA |
| General Chat | qwen3.5-2b-generic-gpu:2-foundry | 2 | NA |
| General Chat | qwen3.5-4b-generic-gpu:2-foundry | 4 | NA |
| General Chat | qwen3.5-9b-generic-gpu:2-foundry | 9 | NA |
| General Chat - OV | qwen2-0.5b-chat-ov | 0.5 | OpenVINO |
| General Chat - OV | qwen3-1.7b-ov | 1.7 | OpenVINO |
| General Chat - OV | qwen3-14b-ov | 14 | OpenVINO |
| General Chat - OV | qwen3-4b-ov | 4 | OpenVINO |
| General Chat - OV | qwen3-8b-ov | 8 | OpenVINO |
| General Chat - OV | dolphin-2.9.4-llama3.1-8b-ov | 8 | OpenVINO |
| General Chat - OV | llama-2-13b-chat-ov | 13 | OpenVINO |
| General Chat - OV | llama-2-chat-ov | 7 | OpenVINO |
| General Chat - OV | tiny-llama-chat-ov | 1.1 | OpenVINO |
| General Chat - OV | phi-3-ov | 3.8 | OpenVINO |
| General Chat - OV | phi-4-ov | 14 | OpenVINO |
| General Chat - OV | phi-4-mini-ov | 3.8 | OpenVINO |
| General Chat - OV | dolphin-2.9.3-mistral-7b-32k-ov | 7 | OpenVINO |
| General Chat - OV | teknium-open-hermes-2.5-mistral-ov | 7 | OpenVINO |
| General Chat - OV | zephyr-mistral-7b-chat-ov | 7 | OpenVINO |
| General Chat - OV | yi-1.5-34b-ov | 34 | OpenVINO |
| General Chat - OV | yi-6b-1.5v-chat-ov | 6 | OpenVINO |
| General Chat - OV | yi-9b-chat-ov | 9 | OpenVINO |
| General Chat - OV | gemma-2-27b-ov | 27 | OpenVINO |
| General Chat - OV | gemma-2b-it-ov | 2 | OpenVINO |
| General Chat - OV | gemma-7b-it-ov | 7 | OpenVINO |
| General Chat - OV | stablelm-2-12b-chat-ov | 12 | OpenVINO |
| General Chat - OV | stablelm-2-zephyr-1_6b-ov | 1.6 | OpenVINO |
| General Chat - OV | stablelm-zephyr-3b-ov | 3 | OpenVINO |
| General Chat - OV | dreamgen-wizardlm-2-7b-ov | 7 | OpenVINO |
| General Chat - OV | granite-4-micro-ov | 1.1 | OpenVINO |
| General Chat - OV | intel-neural-chat-7b-v3-2-ov | 7 | OpenVINO |
| General Chat - OV | openchat-3.6-8b-20240522-ov | 8 | OpenVINO |
| General Chat - OV | tiny-dolphin-2.8-1.1b-ov | 1.1 | OpenVINO |
| General Chat - OV | lcm-dreamshaper-ov | 1.1 | OpenVINO |
| Instruct | qwen2.5-0.5b-instruct-generic-gpu:4-foundry | 0.5 | NA |
| Instruct | qwen2.5-1.5b-instruct-generic-gpu:4-foundry | 1.5 | NA |
| Instruct | qwen2.5-14b-instruct-generic-gpu:4-foundry | 14 | NA |
| Instruct | qwen2.5-7b-instruct-generic-gpu:4-foundry | 7 | NA |
| Instruct | qwen2.5-coder-0.5b-instruct-generic-gpu:4-foundry | 0.5 | NA |
| Instruct | qwen2.5-coder-1.5b-instruct-generic-gpu:4-foundry | 1.5 | NA |
| Instruct | qwen2.5-coder-14b-instruct-generic-gpu:4-foundry | 14 | NA |
| Instruct | qwen2.5-coder-7b-instruct-generic-gpu:4-foundry | 7 | NA |
| Instruct | Phi-4-mini-instruct-generic-gpu:5-foundry | 3.8 | NA |
| Instruct | mistralai-Mistral-7B-Instruct-v0-2-generic-gpu:2-foundry | 7 | NA |
| Instruct | Phi-3-mini-128k-instruct-generic-gpu:2-foundry | 3.8 | NA |
| Instruct | Phi-3-mini-4k-instruct-generic-gpu:2-foundry | 3.8 | NA |
| Instruct | Phi-3.5-mini-instruct-generic-gpu:2-foundry | 3.8 | NA |
| Instruct - ONNX | llama-3.1-instruct-onnx | 8 | ONNX |
| Instruct - ONNX | llama-3.2-1b-instruct-onnx | 1.1 | ONNX |
| Instruct - ONNX | llama-3.2-3b-instruct-onnx | 3 | ONNX |
| Instruct - ONNX | llama-2-chat-onnx | 7 | ONNX |
| Instruct - ONNX | tiny-llama-chat-onnx | 1.1 | ONNX |
| Instruct - ONNX | phi-3-onnx | 3.8 | ONNX |
| Instruct - ONNX | mistral-7b-instruct-v0.3-onnx | 7 | ONNX |
| Instruct - ONNX | gemma-2b-it-onnx | 2 | ONNX |
| Instruct - OV | qwen2-1.5b-instruct-ov | 1.5 | OpenVINO |
| Instruct - OV | qwen2-7b-instruct-ov | 7 | OpenVINO |
| Instruct - OV | qwen2.5-0.5b-instruct-ov | 0.5 | OpenVINO |
| Instruct - OV | qwen2.5-1.5b-instruct-ov | 1.5 | OpenVINO |
| Instruct - OV | qwen2.5-14b-instruct-ov | 14 | OpenVINO |
| Instruct - OV | qwen2.5-32b-instruct-ov | 32 | OpenVINO |
| Instruct - OV | qwen2.5-3b-instruct-ov | 3 | OpenVINO |
| Instruct - OV | qwen2.5-72b-instruct-ov | 72 | OpenVINO |
| Instruct - OV | llama-3.1-instruct-ov | 8 | OpenVINO |
| Instruct - OV | llama-3.2-1b-instruct-ov | 1.1 | OpenVINO |
| Instruct - OV | llama-3.2-3b-instruct-ov | 3 | OpenVINO |
| Instruct - OV | mistral-7b-instruct-v0.2-ov | 7 | OpenVINO |
| Instruct - OV | mistral-7b-instruct-v0.3-ov | 7 | OpenVINO |
| Instruct - OV | mistral-nemo-instruct-2407-ov | 12 | OpenVINO |
| Instruct - OV | mistral-small-instruct-2409-ov | 22 | OpenVINO |
| Language Detector | xlm-roberta-language-detector-ov | 0.28 | OpenVINO |
| Math | mathstral-7b-ov | 7 | OpenVINO |
| Prompt Safety | protectai-prompt-injection-onnx | 0.3 | ONNX |
| Prompt Safety | unitary-toxic-roberta-onnx | 0.1 | ONNX |
| Prompt Safety | valurank-bias-onnx | 0.1 | ONNX |
| Prompt Safety | malicious-url-detector-ov | 0.1 | OpenVINO |
| Prompt Safety | protectai-prompt-injection-ov | 0.3 | OpenVINO |
| Prompt Safety | unitary-toxic-roberta-ov | 0.1 | OpenVINO |
| Prompt Safety | valurank-bias-ov | 0.1 | OpenVINO |
| Question-answer | dragon-mistral-0.3-onnx | 7 | 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-0.3-ov | 7 | OpenVINO |
| Question-answer | dragon-mistral-ov | 7 | OpenVINO |
| Question-answer | dragon-yi-6b-ov | 6 | OpenVINO |
| Question-answer | dragon-yi-9b-ov | 9 | OpenVINO |
| Re-ranker | jina-reranker-tiny-onnx | 0.1 | ONNX |
| Re-ranker | jina-reranker-turbo-onnx | 0.6 | ONNX |
| Re-ranker | jina-reranker-v1-tiny-en-ov | 0.1 | OpenVINO |
| Re-ranker | jina-reranker-v1-turbo-en-ov | 0.6 | OpenVINO |
| Text-to-speech | speech-t5-tts-ov | 0.6 | OpenVINO |
| Vision | phi-3-vision-onnx | 4.2 | ONNX |
| Vision | qwen2.5-vl-3b-ov | 3 | OpenVINO |
| Vision | qwen2.5-vl-7b-ov | 7 | OpenVINO |
| Vision | qwen2-vl-2b-instruct-ov | 2 | OpenVINO |
| Vision | qwen2-vl-7b-instruct-ov | 7 | OpenVINO |
NPU Models
Models designed to run on Neural Processing Units for efficient, low-power inference.
| Category | Model | Parameters | Format |
|---|---|---|---|
| Agentic | slim-emotions-npu-ov | 1.1 | OpenVINO |
| Agentic | slim-extract-tiny-npu-ov | 1.1 | OpenVINO |
| Agentic | slim-intent-npu-ov | 1.1 | OpenVINO |
| Agentic | slim-ner-npu-ov | 1.1 | OpenVINO |
| Agentic | slim-ratings-npu-ov | 1.1 | OpenVINO |
| Agentic | slim-sentiment-npu-ov | 1.1 | OpenVINO |
| Agentic | slim-sql-npu-ov | 1.1 | OpenVINO |
| Agentic | slim-summary-tiny-npu-ov | 1.1 | OpenVINO |
| Agentic | slim-tags-npu-ov | 1.1 | OpenVINO |
| Agentic | slim-topics-npu-ov | 1.1 | OpenVINO |
| General Chat | DeepSeek-R1-Distill-Qwen-7B-vitis-npu:2-foundry | 7 | NA |
| General Chat | Phi-4-mini-reasoning-vitis-npu:2-foundry | 3.8 | NA |
| General Chat | mistral-7b-v0.3-npu-ov | 7 | OpenVINO |
| General Chat | yi-9b-npu-ov | 9 | OpenVINO |
| Instruct | qwen2.5-0.5b-instruct-vitis-npu:3-foundry | 0.5 | NA |
| Instruct | qwen2.5-7b-instruct-vitis-npu:2-foundry | 7 | NA |
| Instruct | qwen2.5-coder-0.5b-instruct-vitis-npu:2-foundry | 0.5 | NA |
| Instruct | qwen2.5-coder-1.5b-instruct-vitis-npu:2-foundry | 1.5 | NA |
| Instruct | qwen2.5-coder-7b-instruct-vitis-npu:2-foundry | 7 | NA |
| Instruct | Phi-4-mini-instruct-vitis-npu:2-foundry | 3.8 | NA |
| Instruct | Mistral-7B-Instruct-v0-2-vitis-npu:2-foundry | 7 | NA |
| Instruct | phi-3-mini-128k-instruct-vitis-npu:2-foundry | 3.8 | NA |
| Instruct | Phi-3-mini-4k-instruct-vitis-npu:2-foundry | 3.8 | NA |
| Instruct | phi-4-mini-instruct-vitis-npu:2-foundry | 3.8 | NA |
Cloud Models
Models that run on remote servers over the internet, increasing speed and complex capabilities.
| Category | Model | Parameters | Format |
|---|---|---|---|
| Cloud | gpt-5.2-pro | NA | Cloud |
| Cloud | gpt-5.2 | NA | Cloud |
| Cloud | gpt-5-mini | NA | Cloud |
| Cloud | gpt-5-nano | NA | Cloud |
| Cloud | gpt-4.1 | NA | Cloud |
| Cloud | claude-opus-4-5 | NA | Cloud |
| Cloud | claude-haiku-4-5 | NA | Cloud |
| Cloud | claude-sonnet-4-5 | NA | Cloud |
| Cloud | claude-sonnet-4-20250514 | NA | Cloud |
| Cloud | claude-opus-4-20250514 | NA | Cloud |
| Cloud | gemini-3-pro-preview | NA | Cloud |
| Cloud | gemini-3-flash-preview | NA | Cloud |
| Cloud | gemini-2.5-pro | NA | Cloud |
| Cloud | gemini-2.5-flash | NA | Cloud |
| Cloud | gemini-2.5-flash-lite | NA | Cloud |
