Filter by type:
Filter by tags:
omega-qwen3-atom-8b
Omega-Qwen3-Atom-8B is a powerful 8B-parameter model fine-tuned on Qwen3-8B using the curated Open-Omega-Atom-1.5M dataset, optimized for math and science reasoning. It excels at symbolic processing, scientific problem-solving, and structured output generation—making it a high-performance model for researchers, educators, and technical developers working in computational and analytical domains.
Repository: localaiLicense: apache-2.0
llama-3.1_openscholar-8b
Llama-3.1_OpenScholar-8B is a fine-tuned 8B for scientific literature synthesis. The Llama-3.1_OpenScholar-8B us trained on the os-data dataset. Developed by: University of Washigton, Allen Institute for AI (AI2)
Repository: localaiLicense: apache-2.0
llama3.1-bestmix-chem-einstein-8b
Llama3.1-BestMix-Chem-Einstein-8B is an innovative, meticulously blended model designed to excel in instruction-following, chemistry-focused tasks, and long-form conversational generation. This model fuses the best qualities of multiple Llama3-based architectures, making it highly versatile for both general and specialized tasks. 💻🧠✨
Repository: localaiLicense: apache-2.0
astrosage-70b
Developed by: AstroMLab (Tijmen de Haan, Yuan-Sen Ting, Tirthankar Ghosal, Tuan Dung Nguyen, Alberto Accomazzi, Emily Herron, Vanessa Lama, Azton Wells, Nesar Ramachandra, Rui Pan)
Funded by:
Oak Ridge Leadership Computing Facility (OLCF), a DOE Office of Science User Facility at Oak Ridge National Laboratory (U.S. Department of Energy).
Microsoft’s Accelerating Foundation Models Research (AFMR) program.
World Premier International Research Center Initiative (WPI), MEXT, Japan.
National Science Foundation (NSF).
UChicago Argonne LLC, Operator of Argonne National Laboratory (U.S. Department of Energy).
Reference Paper: Tijmen de Haan et al. (2025). "AstroMLab 4: Benchmark-Topping Performance in Astronomy Q&A with a 70B-Parameter Domain-Specialized Reasoning Model" https://arxiv.org/abs/2505.17592
Model Type: Autoregressive transformer-based LLM, specialized in astronomy, astrophysics, space science, astroparticle physics, cosmology, and astronomical instrumentation.
Model Architecture: AstroSage-70B is a fine-tuned derivative of the Meta-Llama-3.1-70B architecture, making no architectural changes. The Llama-3.1-70B-Instruct tokenizer is also used without modification.
Context Length: Fine-tuned on 8192-token sequences. Base model was trained to 128k context length.
AstroSage-70B is a large-scale, domain-specialized language model tailored for research and education in astronomy, astrophysics, space science, cosmology, and astronomical instrumentation. It builds on the Llama-3.1-70B foundation model, enhanced through extensive continued pre-training (CPT) on a vast corpus of astronomical literature, further refined with supervised fine-tuning (SFT) on instruction-following datasets, and finally enhanced via parameter averaging (model merging) with other popular fine tunes. AstroSage-70B aims to achieve state-of-the-art performance on astronomy-specific tasks, providing researchers, students, and enthusiasts with an advanced AI assistant. This 70B parameter model represents a significant scaling up from the AstroSage-8B model. The primary enhancements from the AstroSage-8B model are:
Stronger base model, higher parameter count for increased capacity
Improved datasets
Improved learning hyperparameters
Reasoning capability (can be enabled or disabled at inference time)
Training Lineage
Base Model: Meta-Llama-3.1-70B.
Continued Pre-Training (CPT): The base model underwent 2.5 epochs of CPT (168k GPU-hours) on a specialized astronomy corpus (details below, largely inherited from AstroSage-8B) to produce AstroSage-70B-CPT. This stage imbues domain-specific knowledge and language nuances.
Supervised Fine-Tuning (SFT): AstroSage-70B-CPT was then fine-tuned for 0.6 epochs (13k GPU-hours) using astronomy-relevant and general-purpose instruction-following datasets, resulting in AstroSage-70B-SFT.
Final Mixture: The released AstroSage-70B model is created via parameter averaging / model merging:
DARE-TIES with rescale: true and lambda: 1.2
AstroSage-70B-CPT designated as the "base model"
70% AstroSage-70B-SFT (density 0.7)
15% Llama-3.1-Nemotron-70B-Instruct (density 0.5)
7.5% Llama-3.3-70B-Instruct (density 0.5)
7.5% Llama-3.1-70B-Instruct (density 0.5)
Intended Use: Like AstroSage-8B, this model can be used for a variety of LLM application, including
Providing factual information and explanations in astronomy, astrophysics, cosmology, and instrumentation.
Assisting with literature reviews and summarizing scientific papers.
Answering domain-specific questions with high accuracy.
Brainstorming research ideas and formulating hypotheses.
Assisting with programming tasks related to astronomical data analysis.
Serving as an educational tool for learning astronomical concepts.
Potentially forming the core of future agentic research assistants capable of more autonomous scientific tasks.
Repository: localaiLicense: llama3.1
nvidia_nemotron-research-reasoning-qwen-1.5b
Nemotron-Research-Reasoning-Qwen-1.5B is the world’s leading 1.5B open-weight model for complex reasoning tasks such as mathematical problems, coding challenges, scientific questions, and logic puzzles. It is trained using the ProRL algorithm on a diverse and comprehensive set of datasets. Our model has achieved impressive results, outperforming Deepseek’s 1.5B model by a large margin on a broad range of tasks, including math, coding, and GPQA.
This model is for research and development only.
Repository: localaiLicense: cc-by-nc-4.0
mathstral-7b-v0.1-imat
Mathstral 7B is a model specializing in mathematical and scientific tasks, based on Mistral 7B. You can read more in the official blog post https://mistral.ai/news/mathstral/.
Repository: localaiLicense: apache-2.0
flux.1-dev
FLUX.1 [dev] is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions. For more information, please read our blog post.
Key Features
Cutting-edge output quality, second only to our state-of-the-art model FLUX.1 [pro].
Competitive prompt following, matching the performance of closed source alternatives .
Trained using guidance distillation, making FLUX.1 [dev] more efficient.
Open weights to drive new scientific research, and empower artists to develop innovative workflows.
Generated outputs can be used for personal, scientific, and commercial purposes as described in the flux-1-dev-non-commercial-license.
Repository: localaiLicense: flux-1-dev-non-commercial-license
flux.1-schnell
FLUX.1 [schnell] is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions. For more information, please read our blog post.
Key Features
Cutting-edge output quality and competitive prompt following, matching the performance of closed source alternatives.
Trained using latent adversarial diffusion distillation, FLUX.1 [schnell] can generate high-quality images in only 1 to 4 steps.
Released under the apache-2.0 licence, the model can be used for personal, scientific, and commercial purposes.
Repository: localaiLicense: apache-2.0
flux.1-dev-ggml
FLUX.1 [dev] is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions. For more information, please read our blog post.
Key Features
Cutting-edge output quality, second only to our state-of-the-art model FLUX.1 [pro].
Competitive prompt following, matching the performance of closed source alternatives .
Trained using guidance distillation, making FLUX.1 [dev] more efficient.
Open weights to drive new scientific research, and empower artists to develop innovative workflows.
Generated outputs can be used for personal, scientific, and commercial purposes as described in the flux-1-dev-non-commercial-license.
This model is quantized with GGUF
Repository: localaiLicense: flux-1-dev-non-commercial-license
flux.1-kontext-dev
FLUX.1 Kontext [dev] is a 12 billion parameter rectified flow transformer capable of editing images based on text instructions. For more information, please read our blog post and our technical report. You can find information about the [pro] version in here.
Key Features
Change existing images based on an edit instruction.
Have character, style and object reference without any finetuning.
Robust consistency allows users to refine an image through multiple successive edits with minimal visual drift.
Trained using guidance distillation, making FLUX.1 Kontext [dev] more efficient.
Open weights to drive new scientific research, and empower artists to develop innovative workflows.
Generated outputs can be used for personal, scientific, and commercial purposes, as described in the FLUX.1 [dev] Non-Commercial License.
Repository: localaiLicense: flux-1-dev-non-commercial-license
flux.1-dev-ggml-q8_0
FLUX.1 [dev] is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions. For more information, please read our blog post.
Key Features
Cutting-edge output quality, second only to our state-of-the-art model FLUX.1 [pro].
Competitive prompt following, matching the performance of closed source alternatives .
Trained using guidance distillation, making FLUX.1 [dev] more efficient.
Open weights to drive new scientific research, and empower artists to develop innovative workflows.
Generated outputs can be used for personal, scientific, and commercial purposes as described in the flux-1-dev-non-commercial-license.
Repository: localaiLicense: flux-1-dev-non-commercial-license
flux.1-krea-dev-ggml
FLUX.1 Krea [dev] is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions. For more information, please read our blog post and Krea's blog post.
Cutting-edge output quality, with a focus on aesthetic photography.
Competitive prompt following, matching the performance of closed source alternatives.
Trained using guidance distillation, making FLUX.1 Krea [dev] more efficient.
Open weights to drive new scientific research, and empower artists to develop innovative workflows.
Generated outputs can be used for personal, scientific, and commercial purposes, as described in the flux-1-dev-non-commercial-license.
Repository: localaiLicense: flux-1-dev-non-commercial-license
flux.1-krea-dev-ggml-q8_0
FLUX.1 Krea [dev] is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions. For more information, please read our blog post and Krea's blog post.
Cutting-edge output quality, with a focus on aesthetic photography.
Competitive prompt following, matching the performance of closed source alternatives.
Trained using guidance distillation, making FLUX.1 Krea [dev] more efficient.
Open weights to drive new scientific research, and empower artists to develop innovative workflows.
Generated outputs can be used for personal, scientific, and commercial purposes, as described in the flux-1-dev-non-commercial-license.
Repository: localaiLicense: flux-1-dev-non-commercial-license
wraith-8b-i1
**Wraith-8B**
*VANTA Research Entity-001: The Analytical Intelligence*
A highly specialized fine-tune of **Meta's Llama 3.1 8B Instruct**, Wraith-8B excels in **mathematical reasoning, STEM problem-solving, and logical deduction**. Developed as the first in the VANTA Research Entity Series, this model combines a distinctive cosmic intelligence persona with clinical precision to deliver superior performance on benchmark tasks:
- **70% accuracy on GSM8K** (math word problems) — **+37% relative improvement** over the base model
- **58.5% on TruthfulQA** — enhanced factual accuracy
- **76.7% on MMLU Social Sciences** — strong domain-specific reasoning
Trained using a targeted STEM surgical fine-tuning process, Wraith maintains a unique voice: clear, step-by-step, and grounded in logic. Ideal for education, technical analysis, and reasoning-heavy applications.
**Key Features:**
- Base: `meta-llama/Llama-3.1-8B-Instruct`
- Language: English
- Context: 131K tokens
- Quantized versions available (GGUF), including Q4_K_M (4.7GB) for efficient inference
- License: Llama 3.1 Community License
**Use Case:** Mathematical reasoning, scientific analysis, logic puzzles, STEM tutoring, and technical writing with personality.
> *“Calculate first, philosophize second.”*
> — Wraith, The Analytical Intelligence
[Download on Hugging Face](https://huggingface.co/vanta-research/wraith-8B) | [GitHub](https://github.com/vanta-research/wraith-8b)
Repository: localaiLicense: llama3.1
metatune-gpt20b-r1.1-i1
**Model Name:** MetaTune-GPT20B-R1.1
**Base Model:** unsloth/gpt-oss-20b-unsloth-bnb-4bit
**Repository:** [EpistemeAI/metatune-gpt20b-R1.1](https://huggingface.co/EpistemeAI/metatune-gpt20b-R1.1)
**License:** Apache 2.0
**Description:**
MetaTune-GPT20B-R1.1 is a large language model fine-tuned for recursive self-improvement, making it one of the first publicly released models capable of autonomously generating training data, evaluating its own performance, and adjusting its hyperparameters to improve over time. Built upon the open-weight GPT-OSS 20B architecture and trained with Unsloth's optimized 4-bit quantization, this model excels in complex reasoning, agentic tasks, and function calling. It supports tools like web browsing and structured output generation, and is particularly effective in high-reasoning use cases such as scientific problem-solving and math reasoning.
**Performance Highlights (Zero-shot):**
- **GPQA Diamond:** 93.3% exact match
- **GSM8K (Chain-of-Thought):** 100% exact match
**Recommended Use:**
- Advanced reasoning & planning
- Autonomous agent workflows
- Research, education, and technical problem-solving
**Safety Note:**
Use with caution. For safety-critical applications, pair with a safety guardrail model such as [openai/gpt-oss-safeguard-20b](https://huggingface.co/openai/gpt-oss-safeguard-20b).
**Fine-Tuned From:** unsloth/gpt-oss-20b-unsloth-bnb-4bit
**Training Method:** Recursive Self-Improvement on the [Recursive Self-Improvement Dataset](https://huggingface.co/datasets/EpistemeAI/recursive_self_improvement_dataset)
**Framework:** Hugging Face TRL + Unsloth for fast, efficient training
**Inference Tip:** Set reasoning level to "high" for best results and to reduce prompt injection risks.
👉 [View on Hugging Face](https://huggingface.co/EpistemeAI/metatune-gpt20b-R1.1) | [GitHub: Recursive Self-Improvement](https://github.com/openai/harmony)
Repository: localaiLicense: apache-2.0