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
lythri-4b-a2b-q4
Lythri 4B A2B is a Gemma 4 E2B fine-tune for conversational companionship.
This Q4_K_M GGUF build runs text chat through llama.cpp with the embedded
chat template and a 32,768-token context.
Repository: localaiLicense: apache-2.0
lythri-4b-a2b-q8
Lythri 4B A2B is a Gemma 4 E2B fine-tune for conversational companionship.
This Q8_0 GGUF build runs text chat through llama.cpp with the embedded
chat template and a 32,768-token context.
Repository: localaiLicense: apache-2.0
nemotron-3.5-bolt-e4b-q4
NVIDIA Nemotron 3.5 Bolt E4B is a Gemma 4 E4B fine-tune for
conversational assistants, instruction following, and multi-turn tool use.
This UD-Q4_K_XL GGUF build includes the F16 vision projector for
chat and image input, with a 32,768-token context by default.
Repository: localaiLicense: openmdw-1.1
nemotron-3.5-bolt-e4b-q8
NVIDIA Nemotron 3.5 Bolt E4B is a Gemma 4 E4B fine-tune for
conversational assistants, instruction following, and multi-turn tool use.
This UD-Q8_K_XL GGUF build includes the F16 vision projector for
chat and image input, with a 32,768-token context by default.
Repository: localaiLicense: openmdw-1.1
lythri-7b-a4b-q5
Lythri 7B A4B is a Gemma 4 E4B fine-tune for conversational companionship,
with 7.46B total parameters and 4.5B active parameters.
This Q5_K_M GGUF build runs text chat through llama.cpp with the embedded
chat template and a 32,768-token context.
Repository: localaiLicense: apache-2.0
lythri-7b-a4b-q6
Lythri 7B A4B is a Gemma 4 E4B fine-tune for conversational companionship,
with 7.46B total parameters and 4.5B active parameters.
This Q6_K GGUF build runs text chat through llama.cpp with the embedded
chat template and a 32,768-token context.
Repository: localaiLicense: apache-2.0
lythri-7b-a4b-q8
Lythri 7B A4B is a Gemma 4 E4B fine-tune for conversational companionship,
with 7.46B total parameters and 4.5B active parameters.
This Q8_0 GGUF build runs text chat through llama.cpp with the embedded
chat template and a 32,768-token context.
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
Page 1