Foundation models & chat Tools & Software
Foundation models & chat is part of AI on PulseGate. PulseGate tracks 1,619 Foundation models & chat products — 49 indexed in the past week, most recently TimeOmni 1 7B.
TimeOmni-1-7B is a 7B parameter language model with tool-calling capabilities based on Qwen.
qwen2.5-1.5b-instruct-q4_k_m.gguf is a 4-bit quantized GGUF version of the Qwen2.5 1.5B Instruct model.
GLM-4.7-Flash-GGUF is a GGUF-quantized version of the GLM-4.7-Flash language model for local inference.
Qwen-Marketing is a Qwen model fine-tuned for marketing-related tasks and content generation.
deepseek-r1-distill-qwen-32b-awq is an AWQ-quantized distilled version of a DeepSeek reasoning model based on Qwen.
phobert-base-v2 is the second version of a RoBERTa-based model pretrained on Vietnamese text.
tiny-random-BertModel is a minimal random-weight BERT model used for testing and debugging.
opus-mt-mul-en is a multilingual-to-English machine translation model from the OPUS-MT project.
Qwen3-ASR-0.6B-8bit is an 8-bit quantized automatic speech recognition model optimized for MLX.
Multimodal model from Moonshot AI that processes both images and text.
DiffusionGemma is an open-source text-to-image diffusion model based on Gemma, optimized for NVIDIA hardware.
Fara1.5-27B is a Microsoft fine-tuned 27B parameter model based on Qwen for computer use.
Agents-A1-4B is a 4B parameter language model specialized as a deep research assistant.
Mamba2-primed-HQwen3-8B-Instruct is a hybrid Mamba-Transformer model primed with Qwen3 for instruction following.
Qwen3.6-35B-A3B-GGUF is a GGUF quantized version of the Qwen3.6-35B model for efficient local inference.
pplx-embed-v1-0.6b is a compact embedding model developed by Perplexity AI for feature extraction and semantic search.
GLM-5.1-FP8 is a quantized version of the GLM-5.1 large language model in FP8 precision.
Ornith-1.0-9B-FP8-DYNAMIC is a quantized 9B parameter language model optimized for efficient inference.
Mage-VL is a multimodal foundation model for image and video understanding developed by Microsoft.
Perplexity AI embedding model for context feature extraction.
OTel-2.0-LLM-31B-IT is an open-source large language model available on Hugging Face for text generation and chat applications.
A distilled RoBERTa model for question answering, fine-tuned on SQuAD 2.0.
GGUF quantized version of Gemma 4 26B instruction-tuned model.
TranslateGemma-4B is a specialized 4B parameter model for high-quality machine translation.
gemma-4-12B-AWQ is a quantized version of Google's Gemma 4 language model.
Funnel-Transformer is an open-source NLP model for feature extraction available on Hugging Face.
BTL-3 is a 27B open-weight agent model specialized for agentic coding and structural tool use.
Fine-tuned BGE embedding model specialized as a course recommender using sentence similarity.
opus-mt-en-zh is an open-source machine translation model from English to Chinese.
Agents-A1-NVFP4 is an open-source multimodal model optimized for agentic tasks and tool use.
Liquid AI's 1.6B parameter vision-language model with multimodal capabilities.
Ternary-Bonsai-8B-gguf is a quantized GGUF version of an 8B parameter language model.
tiny-random-qwen3-omni is a small random test model for Qwen3-Omni multimodal capabilities.
Gemma-4-31B-it-assistant is an open-source multimodal language model for text generation and any-to-any tasks.
Bonsai-27B-gguf is a quantized open-source 27B language model optimized for local inference with llama.cpp.
Ornith-1.0-35B is an open-source multimodal language model with vision and video understanding capabilities.
Mistral-Small-3.2-24B-Instruct-2506-FP8 is an FP8 quantized version of Mistral Small 3.2 for multimodal instruction following.
A Korean ALBERT base model trained on 70GB of Korean text.
tiny-LlamaForCausalLM-3 is a minimal test model for causal language modeling used in TRL library testing.
tiny-GemmaForCausalLM is a minimal Gemma model used for testing causal language modeling pipelines.
GGUF quantized version of Google's Gemma 3 1B instruction-tuned model for local inference.
Google's 4B parameter Gemma 3 pretrained model for multimodal text and image understanding.
gmunkhtur/paraphrase-multilingual-minilm-l12-v3-mn is a Mongolian-adapted paraphrase model based on MiniLM.
Alias-GPT2-Small-x21 is an open-source language model for text generation hosted on Hugging Face.
EnviT5 is a multilingual T5-based model for English-Vietnamese translation.
NVIDIA Nemotron Nano 12B v2 is an open model optimized for reasoning, tool use, and synthetic data generation.
A tiny test model based on DeepSeek V3 for causal language modeling, used for internal testing.
A quantized instruction-tuned version of Google's Gemma 4 12B model optimized for NVIDIA hardware.
A large language model from the GLM series with advanced reasoning and tool-calling capabilities.
Sup computer is a research studio that builds and releases small open-source language models trainable on consumer hardware.