Filter by type:
Filter by tags:
inkling
# Inkling
BF16 |
NVFP4 |
Playground |
Tinker Cookbook |
Acceptable Use
## 1. General Information
Inkling is a general-purpose multimodal model that accepts text, image and audio inputs and generates text outputs. It is intended for use in English and other languages, and across multiple coding languages. The model is designed to be used by developers building AI-powered applications, including agentic and tool-use systems, coding assistants, chatbots, and retrieval-augmented generation systems, and is suitable for general-purpose conversational use, instruction-following, and other natural language and multimodal tasks. It is released with open weights to support research, fine-tuning and integration into third-party products by downstream developers.
**Languages:** English, with general multilingual capabilities across other languages.
## 2. Getting Started
Try Inkling on the Tinker Playground or access via API using the Tinker Cookbook.
Inkling supports local deployment using the following open-source libraries:
* SGLang (recipe, PR)
* vLLM (recipe, PR)
* TokenSpeed (recipe, PR)
* Unsloth (recipe, PR)
* Huggingface (recipe, PR)
...
Repository: localaiLicense: apache-2.0
qwen_qwen3.5-4b
Qwen3.5-4B is a multimodal LLM with 4 billion parameters, optimized for chat and vision tasks. This GGUF quantized version enables efficient local inference via llama-cpp backend. Supports both text and image input for enhanced conversational capabilities.
Repository: localaiLicense: apache-2.0
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
onerec-8b
The model `mradermacher/OneRec-8B-GGUF` is a quantized version of the base model `OpenOneRec/OneRec-8B`, a large language model designed for tasks like recommendations or content generation. It is optimized for efficiency with various quantization schemes (e.g., Q2_K, Q4_K, Q8_0) and available in multiple sizes (3.5–9.0 GB). The model uses the GGUF format and is licensed under Apache-2.0. Key features include:
- **Base Model**: `OpenOneRec/OneRec-8B` (a pre-trained language model for recommendations).
- **Quantization**: Supports multiple quantized variants (Q2_K, Q3_K, Q4_K, etc.), with the best quality for `Q4_K_S` and `Q8_0`.
- **Sizes**: Available in sizes ranging from 3.5 GB (Q2_K) to 9.0 GB (Q8_0), with faster speeds for lower-bit quantized versions.
- **Usage**: Compatible with GGUF files, suitable for deployment in applications requiring efficient model inference.
- **Licence**: Apache-2.0, available at [https://huggingface.co/OpenOneRec/OneRec-8B/blob/main/LICENSE](https://huggingface.co/OpenOneRec/OneRec-8B/blob/main/LICENSE).
For detailed specifications, refer to the [model page](https://hf.tst.eu/model#OneRec-8B-GGUF).
Repository: localaiLicense: apache-2.0
qwen3-30b-a3b
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features:
Uniquely support of seamless switching between thinking mode (for complex logical reasoning, math, and coding) and non-thinking mode (for efficient, general-purpose dialogue) within single model, ensuring optimal performance across various scenarios.
Significantly enhancement in its reasoning capabilities, surpassing previous QwQ (in thinking mode) and Qwen2.5 instruct models (in non-thinking mode) on mathematics, code generation, and commonsense logical reasoning.
Superior human preference alignment, excelling in creative writing, role-playing, multi-turn dialogues, and instruction following, to deliver a more natural, engaging, and immersive conversational experience.
Expertise in agent capabilities, enabling precise integration with external tools in both thinking and unthinking modes and achieving leading performance among open-source models in complex agent-based tasks.
Support of 100+ languages and dialects with strong capabilities for multilingual instruction following and translation.
Qwen3-30B-A3B has the following features:
Type: Causal Language Models
Training Stage: Pretraining & Post-training
Number of Parameters: 30.5B in total and 3.3B activated
Number of Paramaters (Non-Embedding): 29.9B
Number of Layers: 48
Number of Attention Heads (GQA): 32 for Q and 4 for KV
Number of Experts: 128
Number of Activated Experts: 8
Context Length: 32,768 natively and 131,072 tokens with YaRN.
For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our blog, GitHub, and Documentation.
Repository: localaiLicense: apache-2.0
qwen3-32b
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features:
Uniquely support of seamless switching between thinking mode (for complex logical reasoning, math, and coding) and non-thinking mode (for efficient, general-purpose dialogue) within single model, ensuring optimal performance across various scenarios.
Significantly enhancement in its reasoning capabilities, surpassing previous QwQ (in thinking mode) and Qwen2.5 instruct models (in non-thinking mode) on mathematics, code generation, and commonsense logical reasoning.
Superior human preference alignment, excelling in creative writing, role-playing, multi-turn dialogues, and instruction following, to deliver a more natural, engaging, and immersive conversational experience.
Expertise in agent capabilities, enabling precise integration with external tools in both thinking and unthinking modes and achieving leading performance among open-source models in complex agent-based tasks.
Support of 100+ languages and dialects with strong capabilities for multilingual instruction following and translation.
Qwen3-32B has the following features:
Type: Causal Language Models
Training Stage: Pretraining & Post-training
Number of Parameters: 32.8B
Number of Paramaters (Non-Embedding): 31.2B
Number of Layers: 64
Number of Attention Heads (GQA): 64 for Q and 8 for KV
Context Length: 32,768 natively and 131,072 tokens with YaRN.
For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our blog, GitHub, and Documentation.
Repository: localaiLicense: apache-2.0
qwen3-14b
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features:
Uniquely support of seamless switching between thinking mode (for complex logical reasoning, math, and coding) and non-thinking mode (for efficient, general-purpose dialogue) within single model, ensuring optimal performance across various scenarios.
Significantly enhancement in its reasoning capabilities, surpassing previous QwQ (in thinking mode) and Qwen2.5 instruct models (in non-thinking mode) on mathematics, code generation, and commonsense logical reasoning.
Superior human preference alignment, excelling in creative writing, role-playing, multi-turn dialogues, and instruction following, to deliver a more natural, engaging, and immersive conversational experience.
Expertise in agent capabilities, enabling precise integration with external tools in both thinking and unthinking modes and achieving leading performance among open-source models in complex agent-based tasks.
Support of 100+ languages and dialects with strong capabilities for multilingual instruction following and translation.
Qwen3-14B has the following features:
Type: Causal Language Models
Training Stage: Pretraining & Post-training
Number of Parameters: 14.8B
Number of Paramaters (Non-Embedding): 13.2B
Number of Layers: 40
Number of Attention Heads (GQA): 40 for Q and 8 for KV
Context Length: 32,768 natively and 131,072 tokens with YaRN.
For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our blog, GitHub, and Documentation.
Repository: localaiLicense: apache-2.0
qwen3-8b
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features:
Uniquely support of seamless switching between thinking mode (for complex logical reasoning, math, and coding) and non-thinking mode (for efficient, general-purpose dialogue) within single model, ensuring optimal performance across various scenarios.
Significantly enhancement in its reasoning capabilities, surpassing previous QwQ (in thinking mode) and Qwen2.5 instruct models (in non-thinking mode) on mathematics, code generation, and commonsense logical reasoning.
Superior human preference alignment, excelling in creative writing, role-playing, multi-turn dialogues, and instruction following, to deliver a more natural, engaging, and immersive conversational experience.
Expertise in agent capabilities, enabling precise integration with external tools in both thinking and unthinking modes and achieving leading performance among open-source models in complex agent-based tasks.
Support of 100+ languages and dialects with strong capabilities for multilingual instruction following and translation.
Model Overview
Qwen3-8B has the following features:
Type: Causal Language Models
Training Stage: Pretraining & Post-training
Number of Parameters: 8.2B
Number of Paramaters (Non-Embedding): 6.95B
Number of Layers: 36
Number of Attention Heads (GQA): 32 for Q and 8 for KV
Context Length: 32,768 natively and 131,072 tokens with YaRN.
Repository: localaiLicense: apache-2.0
qwen3-4b
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features:
Uniquely support of seamless switching between thinking mode (for complex logical reasoning, math, and coding) and non-thinking mode (for efficient, general-purpose dialogue) within single model, ensuring optimal performance across various scenarios.
Significantly enhancement in its reasoning capabilities, surpassing previous QwQ (in thinking mode) and Qwen2.5 instruct models (in non-thinking mode) on mathematics, code generation, and commonsense logical reasoning.
Superior human preference alignment, excelling in creative writing, role-playing, multi-turn dialogues, and instruction following, to deliver a more natural, engaging, and immersive conversational experience.
Expertise in agent capabilities, enabling precise integration with external tools in both thinking and unthinking modes and achieving leading performance among open-source models in complex agent-based tasks.
Support of 100+ languages and dialects with strong capabilities for multilingual instruction following and translation.
Qwen3-4B has the following features:
Type: Causal Language Models
Training Stage: Pretraining & Post-training
Number of Parameters: 4.0B
Number of Paramaters (Non-Embedding): 3.6B
Number of Layers: 36
Number of Attention Heads (GQA): 32 for Q and 8 for KV
Context Length: 32,768 natively and 131,072 tokens with YaRN.
Repository: localaiLicense: apache-2.0
qwen3-1.7b
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features:
Uniquely support of seamless switching between thinking mode (for complex logical reasoning, math, and coding) and non-thinking mode (for efficient, general-purpose dialogue) within single model, ensuring optimal performance across various scenarios.
Significantly enhancement in its reasoning capabilities, surpassing previous QwQ (in thinking mode) and Qwen2.5 instruct models (in non-thinking mode) on mathematics, code generation, and commonsense logical reasoning.
Superior human preference alignment, excelling in creative writing, role-playing, multi-turn dialogues, and instruction following, to deliver a more natural, engaging, and immersive conversational experience.
Expertise in agent capabilities, enabling precise integration with external tools in both thinking and unthinking modes and achieving leading performance among open-source models in complex agent-based tasks.
Support of 100+ languages and dialects with strong capabilities for multilingual instruction following and translation.
Qwen3-1.7B has the following features:
Type: Causal Language Models
Training Stage: Pretraining & Post-training
Number of Parameters: 1.7B
Number of Paramaters (Non-Embedding): 1.4B
Number of Layers: 28
Number of Attention Heads (GQA): 16 for Q and 8 for KV
Context Length: 32,768
Repository: localaiLicense: apache-2.0
qwen3-0.6b
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features:
Uniquely support of seamless switching between thinking mode (for complex logical reasoning, math, and coding) and non-thinking mode (for efficient, general-purpose dialogue) within single model, ensuring optimal performance across various scenarios.
Significantly enhancement in its reasoning capabilities, surpassing previous QwQ (in thinking mode) and Qwen2.5 instruct models (in non-thinking mode) on mathematics, code generation, and commonsense logical reasoning.
Superior human preference alignment, excelling in creative writing, role-playing, multi-turn dialogues, and instruction following, to deliver a more natural, engaging, and immersive conversational experience.
Expertise in agent capabilities, enabling precise integration with external tools in both thinking and unthinking modes and achieving leading performance among open-source models in complex agent-based tasks.
Support of 100+ languages and dialects with strong capabilities for multilingual instruction following and translation.
Qwen3-0.6B has the following features:
Type: Causal Language Models
Training Stage: Pretraining & Post-training
Number of Parameters: 0.6B
Number of Paramaters (Non-Embedding): 0.44B
Number of Layers: 28
Number of Attention Heads (GQA): 16 for Q and 8 for KV
Context Length: 32,768
Repository: localaiLicense: apache-2.0
shuttleai_shuttle-3.5
A fine-tuned version of Qwen3 32b, emulating the writing style of Claude 3 models and thoroughly trained on role-playing data.
Uniquely support of seamless switching between thinking mode (for complex logical reasoning, math, and coding) and non-thinking mode (for efficient, general-purpose dialogue) within single model, ensuring optimal performance across various scenarios.
Significantly enhancement in its reasoning capabilities, surpassing previous QwQ (in thinking mode) and Qwen2.5 instruct models (in non-thinking mode) on mathematics, code generation, and commonsense logical reasoning.
Superior human preference alignment, excelling in creative writing, role-playing, multi-turn dialogues, and instruction following, to deliver a more natural, engaging, and immersive conversational experience.
Expertise in agent capabilities, enabling precise integration with external tools in both thinking and unthinking modes and achieving leading performance among open-source models in complex agent-based tasks.
Support of 100+ languages and dialects with strong capabilities for multilingual instruction following and translation.
Shuttle 3.5 has the following features:
Type: Causal Language Models
Training Stage: Pretraining & Post-training
Number of Parameters: 32.8B
Number of Paramaters (Non-Embedding): 31.2B
Number of Layers: 64
Number of Attention Heads (GQA): 64 for Q and 8 for KV
Context Length: 32,768 natively and 131,072 tokens with YaRN.
Repository: localaiLicense: apache-2.0
mini-hydra
A specialized reasoning-focused MoE model based on Qwen3-30B-A3Bn
Mini-Hydra is a Mixture-of-Experts (MoE) language model designed for efficient reasoning and faster conclusion generation. Built upon the Qwen3-30B-A3B architecture, this model aims to bridge the performance gap between sparse MoE models and their dense counterparts while maintaining computational efficiency.
The model was trained on a carefully curated combination of reasoning-focused datasets:
Tesslate/Gradient-Reasoning: Advanced reasoning problems with step-by-step solutions
Daemontatox/curated_thoughts_convs: Curated conversational data emphasizing thoughtful responses
Daemontatox/natural_reasoning: Natural language reasoning examples and explanations
Daemontatox/numina_math_cconvs: Mathematical conversation and problem-solving data
Repository: localaiLicense: apache-2.0
moe-girl-1ba-7bt-i1
A finetune of OLMoE by AllenAI designed for roleplaying (and maybe general usecases if you try hard enough).
PLEASE do not expect godliness out of this, it's a model with 1 billion active parameters. Expect something more akin to Gemma 2 2B, not Llama 3 8B.
Repository: localaiLicense: apache-2.0
llama-3.2-sun-2.5b-chat
Base Model
Llama 3.2 1B
Extended Size
1B to 2.5B parameters
Extension Method
Proprietary technique developed by MedIT Solutions
Fine-tuning
Open (or open subsets allowing for commercial use) open datasets from HF
Open (or open subsets allowing for commercial use) SFT datasets from HF
Training Status
Current version: chat-1.0.0
Key Features
Built on Llama 3.2 architecture
Expanded from 1B to 2.47B parameters
Optimized for open-ended conversations
Incorporates supervised fine-tuning for improved performance
Use Case
General conversation and task-oriented interactions
Repository: localaiLicense: llama3.2
llama-doctor-3.2-3b-instruct
The Llama-Doctor-3.2-3B-Instruct model is designed for text generation tasks, particularly in contexts where instruction-following capabilities are needed. This model is a fine-tuned version of the base Llama-3.2-3B-Instruct model and is optimized for understanding and responding to user-provided instructions or prompts. The model has been trained on a specialized dataset, avaliev/chat_doctor, to enhance its performance in providing conversational or advisory responses, especially in medical or technical fields.
Repository: localaiLicense: mit
onellm-doey-v1-llama-3.2-3b
This model is a fine-tuned version of LLaMA 3.2-3B, optimized using LoRA (Low-Rank Adaptation) on the NVIDIA ChatQA-Training-Data. It is tailored for conversational AI, question answering, and other instruction-following tasks, with support for sequences up to 1024 tokens.
Repository: localaiLicense: apache-2.0
llama-sentient-3.2-3b-instruct
The Llama-Sentient-3.2-3B-Instruct model is a fine-tuned version of the Llama-3.2-3B-Instruct model, optimized for text generation tasks, particularly where instruction-following abilities are critical. This model is trained on the mlabonne/lmsys-arena-human-preference-55k-sharegpt dataset, which enhances its performance in conversational and advisory contexts, making it suitable for a wide range of applications.
Repository: localaiLicense: creativeml-openrail-m
llama-smoltalk-3.2-1b-instruct
The Llama-SmolTalk-3.2-1B-Instruct model is a lightweight, instruction-tuned model designed for efficient text generation and conversational AI tasks. With a 1B parameter architecture, this model strikes a balance between performance and resource efficiency, making it ideal for applications requiring concise, contextually relevant outputs. The model has been fine-tuned to deliver robust instruction-following capabilities, catering to both structured and open-ended queries.
Key Features:
Instruction-Tuned Performance: Optimized to understand and execute user-provided instructions across diverse domains.
Lightweight Architecture: With just 1 billion parameters, the model provides efficient computation and storage without compromising output quality.
Versatile Use Cases: Suitable for tasks like content generation, conversational interfaces, and basic problem-solving.
Intended Applications:
Conversational AI: Engage users with dynamic and contextually aware dialogue.
Content Generation: Produce summaries, explanations, or other creative text outputs efficiently.
Instruction Execution: Follow user commands to generate precise and relevant responses.
Repository: localaiLicense: creativeml-openrail-m
llama-chat-summary-3.2-3b
Llama-Chat-Summary-3.2-3B is a fine-tuned model designed for generating context-aware summaries of long conversational or text-based inputs. Built on the meta-llama/Llama-3.2-3B-Instruct foundation, this model is optimized to process structured and unstructured conversational data for summarization tasks.
Repository: localaiLicense: creativeml-openrail-m
LocalAI-functioncall-llama3.2-1b-v0.4
A model tailored to be conversational and execute function calls with LocalAI. This model is based on llama 3.2 and has 1B parameter. Perfect for small devices.
Repository: localaiLicense: apache-2.0
Page 1