Model Hub

Browse PQC-verified AI models, datasets, and tools

All Models Datasets Tools
Sort: Most Downloaded Most Liked Recently Updated
Risk: All CRITICAL HIGH MEDIUM LOW
M
meta-llama/Llama-3.3-70B-Instruct HF Ollama PQC Verified

Meta's most capable open-weight model. 70B parameters with 128K context window, multilingual support, and tool use.

TransformerText Generation70BInstructTool Use CRITICAL
M
meta-llama/Llama-3.1-8B-Instruct HF Ollama PQC Verified

Meta's Llama 3.1 8B parameter instruction-tuned model. Optimized for dialogue and instruction following with 128K context.

TransformerText Generation8BInstruct CRITICAL
M
meta-llama/Llama-3.2-1B-Instruct HF PQC Verified

Text GenerationTransformersSafetensorsLLaMAFacebookMeta HIGH
M
meta-llama/Llama-3.2-3B-Instruct HF Ollama PQC Verified

Compact 3B parameter Llama model optimized for on-device and edge deployment scenarios.

TransformerText Generation3BInstructEdge HIGH
M
meta-llama/Meta-Llama-3-8B HF Ollama PQC Verified

Meta's Llama 3 base model with 8B parameters. Pre-trained on 15T tokens with a 8K context window.

TransformerText Generation8BBase CRITICAL
T
TinyLlama/TinyLlama-1.1B-Chat-v1.0 HF Ollama PQC Verified

Compact 1.1B chat model trained on 3T tokens. Punches above its weight class for edge deployment.

TransformerText Generation1.1BChatEdge MEDIUM
D
deepseek-ai/DeepSeek-R1-Distill-Llama-8B HF PQC Verified

Text GenerationTransformersSafetensorsLLaMAConversationalText Generation CRITICAL
L
lmg-anon/vntl-llama3-8b-v2-gguf HF PQC Verified

TranslationGGUFBase_model:rinna/llama-3-Youko-8bBase_model:quantized:rinna/llama-3-Youko-8bConversationalJapanese HIGH
M
meta-llama/Llama-2-7b-hf HF PQC Verified

Text GenerationTransformersPyTorchSafetensorsLLaMAFacebook CRITICAL
N
nvidia/Llama-3.1-Nemotron-70B-Instruct HF PQC Verified

NVIDIA's optimized Llama 3.1 70B. Custom alignment for helpfulness with strong benchmark performance.

TransformerText Generation70BInstructRLHF CRITICAL
H
hmellor/tiny-random-LlamaForCausalLM HF PQC Verified

Text GenerationTransformersSafetensorsLLaMAConversationalText Generation HIGH
R
RedHatAI/Llama-3.2-1B-Instruct-FP8-dynamic HF PQC Verified

Text GenerationSafetensorsLLaMAFp8VllmConversational HIGH
N
NousResearch/Hermes-3-Llama-3.1-8B HF Ollama PQC Verified

Nous Research's Hermes 3 built on Llama 3.1. Strong function calling, structured output, and agentic capabilities.

TransformerText Generation8BInstructAgentic HIGH
R
root-signals/RootSignals-Judge-Llama-70B HF PQC Verified

Text GenerationSafetensorsGGUFLLaMALlm-As-JudgeEvaluation CRITICAL
Showing 14 of 14 items (page 1 of 1)
Prev Next