Filter by type:
Filter by tags:
hemmingway-1
Hemmingway-1 is Altworld's English-first 27B text model, fine-tuned from Qwen3.8-27B for everyday messages and creative writing.
This Q4_K_M GGUF build uses llama.cpp and the model's embedded chat template. Licensed under CC BY-NC 4.0; commercial use requires a separate agreement.
Repository: localaiLicense: cc-by-nc-4.0
hemmingway-1-q8
Hemmingway-1 is Altworld's English-first 27B text model, fine-tuned from Qwen3.8-27B for everyday messages and creative writing.
This Q8_0 GGUF build uses llama.cpp and the model's embedded chat template. Licensed under CC BY-NC 4.0; commercial use requires a separate agreement.
Repository: localaiLicense: cc-by-nc-4.0
qwen3.6-27b-nvfp4-vllm-cpp
Qwen3.6-27B in NVFP4, served by vllm.cpp: LocalAI's own C++ port of vLLM, with
no Python at inference time. This is the reference text-generation checkpoint
the engine is gated on, token-for-token identical to vLLM's own greedy output
over the 235-prompt correctness battery, and measured at or above vLLM's
throughput at every concurrency from 1 to 32.
The weights are PINNED to revision 890bdef7. That pin is load-bearing, not
housekeeping: the same repository name was later re-quantized to FP8 W8A8
throughout, so an unpinned copy of this entry serves entirely different
weights with no error and none of the measured behaviour above.
Needs a Blackwell-class NVIDIA GPU (NVFP4 has no kernel on older
architectures) and roughly 25 GB of weights plus KV cache. Tool calling and
the thinking split are parsed inside the engine.
Repository: localaiLicense: apache-2.0
deepseek-ai.deepseek-v3.2
This is a quantized version of the DeepSeek-V3.2 model by deepseek-ai, optimized for efficient deployment. It is designed for text generation tasks and supports the pipeline tag `text-generation`. The model is based on the original DeepSeek-V3.2 architecture and is available for use in various applications. For more details, refer to the [official repository](https://github.com/DevQuasar/deepseek-ai.DeepSeek-V3.2-GGUF).
Repository: localai
mox-small-1-i1
The model, **vanta-research/mox-small-1**, is a small-scale text-generation model optimized for conversational AI tasks. It supports chat, persona research, and chatbot applications. The quantized versions (e.g., i1-Q4_K_M, i1-Q4_K_S) are available for efficient deployment, with the i1-Q4_K_S variant offering the best balance of size, speed, and quality. The model is designed for lightweight inference and is compatible with frameworks like HuggingFace Transformers.
Repository: localaiLicense: apache-2.0
liquidai.lfm2-2.6b-transcript
This is a large language model (2.6B parameters) designed for text-generation tasks. It is a quantized version of the original model `LiquidAI/LFM2-2.6B-Transcript`, optimized for efficiency while retaining strong performance. The model is built on the foundation of the base model, with additional optimizations for deployment and use cases like transcription or language modeling. It is trained on large-scale text data and supports multiple languages.
Repository: localai
rwkv7-g1c-13.3b
The model is **RWKV7 g1c 13B**, a large language model optimized for efficiency. It is quantized using **Bartowski's calibrationv5 for imatrix** to reduce memory usage while maintaining performance. The base model is **BlinkDL/rwkv7-g1**, and this version is tailored for text-generation tasks. It balances accuracy and efficiency, making it suitable for deployment in various applications.
Repository: localaiLicense: apache-2.0
liquidai_lfm2-350m-extract
Based on LFM2-350M, LFM2-350M-Extract is designed to extract important information from a wide variety of unstructured documents (such as articles, transcripts, or reports) into structured outputs like JSON, XML, or YAML.
Use cases:
Extracting invoice details from emails into structured JSON.
Converting regulatory filings into XML for compliance systems.
Transforming customer support tickets into YAML for analytics pipelines.
Populating knowledge graphs with entities and attributes from unstructured reports.
You can find more information about other task-specific models in this blog post.
Repository: localaiLicense: lfm1.0
gpt-oss-120b
Welcome to the gpt-oss series, OpenAIâs open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
Weâre releasing two flavors of the open models:
gpt-oss-120b â for production, general purpose, high reasoning use cases that fits into a single H100 GPU (117B parameters with 5.1B active parameters)
gpt-oss-20b â for lower latency, and local or specialized use cases (21B parameters with 3.6B active parameters)
Both models were trained on our harmony response format and should only be used with the harmony format as it will not work correctly otherwise.
This model card is dedicated to the smaller gpt-oss-20b model. Check out gpt-oss-120b for the larger model.
Highlights
Permissive Apache 2.0 license: Build freely without copyleft restrictions or patent riskâideal for experimentation, customization, and commercial deployment.
Configurable reasoning effort: Easily adjust the reasoning effort (low, medium, high) based on your specific use case and latency needs.
Full chain-of-thought: Gain complete access to the modelâs reasoning process, facilitating easier debugging and increased trust in outputs. Itâs not intended to be shown to end users.
Fine-tunable: Fully customize models to your specific use case through parameter fine-tuning.
Agentic capabilities: Use the modelsâ native capabilities for function calling, web browsing, Python code execution, and Structured Outputs.
Native MXFP4 quantization: The models are trained with native MXFP4 precision for the MoE layer, making gpt-oss-120b run on a single H100 GPU and the gpt-oss-20b model run within 16GB of memory.
Repository: localaiLicense: apache-2.0
huihui-ai_huihui-gpt-oss-20b-bf16-abliterated
This is an uncensored version of unsloth/gpt-oss-20b-BF16 created with abliteration (see remove-refusals-with-transformers to know more about it).
Repository: localaiLicense: apache-2.0
l3.3-70b-euryale-v2.3
A direct replacement / successor to Euryale v2.2, not Hanami-x1, though it is slightly better than them in my opinion.
Repository: localaiLicense: llama3
steelskull_l3.3-cu-mai-r1-70b
Cu-Mai, a play on San-Mai for Copper-Steel Damascus, represents a significant evolution in the three-part model series alongside San-Mai (OG) and Mokume-Gane. While maintaining the grounded and reliable nature of San-Mai, Cu-Mai introduces its own distinct "flavor" in terms of prose and overall vibe. The model demonstrates strong adherence to prompts while offering a unique creative expression.
L3.3-Cu-Mai-R1-70b integrates specialized components through the SCE merge method:
EVA and EURYALE foundations for creative expression and scene comprehension
Cirrus and Hanami elements for enhanced reasoning capabilities
Anubis components for detailed scene description
Negative_LLAMA integration for balanced perspective and response
Users consistently praise Cu-Mai for its:
Exceptional prose quality and natural dialogue flow
Strong adherence to prompts and creative expression
Improved coherency and reduced repetition
Performance on par with the original model
While some users note slightly reduced intelligence compared to the original, this trade-off is generally viewed as minimal and doesn't significantly impact the overall experience. The model's reasoning capabilities can be effectively activated through proper prompting techniques.
Repository: localaiLicense: llama3.3
steelskull_l3.3-electra-r1-70b
L3.3-Electra-R1-70b is the newest release of the Unnamed series, this is the 6th iteration based of user feedback.
Built on a custom DeepSeek R1 Distill base (TheSkullery/L3.1x3.3-Hydroblated-R1-70B-v4.4), Electra-R1 integrates specialized components through the SCE merge method. The model uses float32 dtype during processing with a bfloat16 output dtype for optimized performance.
Electra-R1 serves newest gold standard and baseline. User feedback consistently highlights its superior intelligence, coherence, and unique ability to provide deep character insights. Through proper prompting, the model demonstrates advanced reasoning capabilities and unprompted exploration of character inner thoughts and motivations.
The model utilizes the custom Hydroblated-R1 base, created for stability and enhanced reasoning. The SCE merge method's settings are precisely tuned based on extensive community feedback (of over 10 diffrent models from Nevoria to Cu-Mai), ensuring optimal component integration while maintaining model coherence and reliability. This foundation establishes Electra-R1 as the benchmark upon which its variant models build and expand.
Repository: localaiLicense: eva-llama3.3
rwkv-6-world-7b
RWKV (pronounced RwaKuv) is an RNN with GPT-level LLM performance, and can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7.
So it's combining the best of RNN and transformer - great performance, fast inference, fast training, saves VRAM, "infinite" ctxlen, and free text embedding. Moreover it's 100% attention-free, and a Linux Foundation AI project.
Repository: localaiLicense: apache-2.0
opencoder-1.5b-base
The model is a large language model with 1.5 billion parameters, trained on 2.5 trillion tokens of code-related data. It supports both English and Chinese languages and is part of the OpenCoder LLM family which also includes 8B base and chat models. The model achieves high performance across multiple language model benchmarks and is one of the most comprehensively open-sourced models available.
Repository: localaiLicense: inf
finemath-llama-3b
This is a continual-pre-training of Llama-3.2-3B on a mix of đ FineMath (our new high quality math dataset) and FineWeb-Edu.
The model demonstrates superior math performance compared to Llama 3.2 3B, while maintaining similar performance on knowledge, reasoning, and common sense benchmarks.
It was trained on 160B tokens using a mix of 40% FineWeb-Edu and 60% from FineMath (30% FineMath-4+ subset and 30% InfiWebMath-4+ subset). We use nanotron for the training, and you can find the training scripts in our SmolLM2 GitHub repo.
Repository: localaiLicense: apache-2.0
l3.1-8b-llamoutcast-i1
Warning: this model is utterly cursed.
Llamoutcast
This model was originally intended to be a DADA finetune of Llama-3.1-8B-Instruct but the results were unsatisfactory. So it received some additional finetuning on a rawtext dataset and now it is utterly cursed.
It responds to Llama-3 Instruct formatting.
Repository: localaiLicense: cc-by-nc-4.0
mistral-7b-instruct-v0.3
The Mistral-7B-Instruct-v0.3 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-7B-v0.3.
Mistral-7B-v0.3 has the following changes compared to Mistral-7B-v0.2
Extended vocabulary to 32768
Supports v3 Tokenizer
Supports function calling
Repository: localaiLicense: apache-2.0
krutrim-ai-labs_krutrim-2-instruct
Krutrim-2 is a 12B parameter language model developed by the OLA Krutrim team. It is built on the Mistral-NeMo 12B architecture and trained across various domains, including web data, code, math, Indic languages, Indian context data, synthetic data, and books. Following pretraining, the model was finetuned for instruction following on diverse data covering a wide range of tasks, including knowledge recall, math, reasoning, coding, safety, and creative writing.
Repository: localaiLicense: krutrim-community-license-agreement-version-1.0
sicariussicariistuff_redemption_wind_24b
This is a lightly fine-tuned version of the Mistral 24B base model, designed as an accessible and adaptable foundation for further fine-tuning and merging fodder. Key modifications include:
ChatML-ified, with no additional tokens introduced.
High quality private instructânot generated by ChatGPT or Claude, ensuring no slop and good markdown understanding.
No refusalsâsince itâs a base model, refusals should be minimal to non-existent, though, in early testing, occasional warnings still appear (I assume some were baked into the pre-train).
High-quality private creative writing dataset Mainly to dilute baked-in slop further, but it can actually write some stories, not bad for loss ~8.
Small, high-quality private RP dataset This was done so further tuning for RP will be easier. The dataset was kept small and contains ZERO SLOP, some entries are of 16k token length.
Exceptional adherence to character cards This was done to make it easier for further tunes intended for roleplay.
Repository: localaiLicense: apache-2.0
logics-qwen3-math-4b
**Model Name:** Logics-Qwen3-Math-4B
**Base Model:** Qwen/Qwen3-4B-Thinking-2507
**Size:** 4B parameters
**Fine-Tuned For:** Mathematical reasoning, logical problem solving, and algorithmic coding
**Training Data:** OpenMathReasoning, OpenCodeReasoning, Helios-R-6M
**Description:**
A lightweight, high-precision 4B-parameter model optimized for mathematical and logical reasoning. Fine-tuned from Qwen3-4B-Thinking-2507, it excels in solving equations, performing step-by-step reasoning, and handling algorithmic tasks with structured outputs in LaTeX, Markdown, JSON, and more. Ideal for education, research, and deployment on mid-range hardware.
**Use Case:**
Perfect for math problem-solving, code reasoning, and technical content generation in resource-constrained environments.
**Tags:** #math #code #reasoning #4B #Qwen3 #text-generation #open-source
Repository: localaiLicense: apache-2.0
Page 1