Model Gallery
Discover and install AI models from our curated collection
Find Your Perfect Model
Filter by Model Type
Browse by Tags
gemma-4-12b-coder-fable5-composer2.5-v1
Hugging Face |
GitHub |
Launch Blog |
Documentation
License: Apache 2.0 | Authors: Google DeepMind
> [!Note]
> This model card is for the Gemma 4 12B Unified model, which is part of the Gemma 4 family of open models. Built with the same multimodal functionality as Gemma 4 E2B and E4B (text, audio, image, and video inputs), it brings native audio and vision understanding directly to local environments without the need for separate encoders. This unified approach to multimodality makes the model encoder-free, offering a deployment size that is perfect for consumer devices and streamlined local execution.
Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants. Gemma 4 features a context window of up to 256K tokens and maintains multilingual support in over 140 languages.
...
Repository: localaiLicense: gemma
gemma-4-26b-a4b-it-qat
Hugging Face |
GitHub |
Launch Blog |
Documentation
License: Apache 2.0 | Authors: Google DeepMind
> [!Note]
> This model card is for the new versions of the Gemma 4 family optimized with Quantization-Aware Training (QAT), which allows preserving similar quality to bfloat16 while dramatically reducing the memory requirements to load the model.
> Four versions of the QAT checkpoints are available:
> * **Unquantized QAT checkpoints** (Q4_0): Half-precision weights extracted from the QAT pipeline, ideal for custom downstream compilation and research. Available for Gemma 4 E2B, E4B, 12B, 26B A4B, and 31B, and their drafter models.
> * **GGUF** (Q4_0): Ready-to-deploy formats for broad ecosystem compatibility. Available for Gemma 4 E2B, E4B, 12B, 26B A4B, and 31B.
> * **Mobile-optimized** (wNa8o8): A custom schema engineered explicitly for mobile hardware efficiency. It features targeted 2-bit decoding layers, optimized KV caches, and static activations to maximize VRAM savings. Available for Gemma 4 E2B and E4B.
> * **Compressed Tensors** (w4a16): QAT checkpoints serialized in the compressed-tensors format for native, optimized inference with vLLM. Available for Gemma 4 E2B, E4B, 12B
...
Repository: localaiLicense: apache-2.0
gemma-4-12b-it-qat-q4_0
Hugging Face |
GitHub |
Launch Blog |
Documentation
License: Apache 2.0 | Authors: Google DeepMind
> [!Note]
> This model card is for the new versions of the Gemma 4 family optimized with Quantization-Aware Training (QAT), which allows preserving similar quality to bfloat16 while dramatically reducing the memory requirements to load the model.
> Four versions of the QAT checkpoints are available:
> * **Unquantized QAT checkpoints** (Q4_0): Half-precision weights extracted from the QAT pipeline, ideal for custom downstream compilation and research. Available for Gemma 4 E2B, E4B, 12B, 26B A4B, and 31B, and their drafter models.
> * **GGUF** (Q4_0): Ready-to-deploy formats for broad ecosystem compatibility. Available for Gemma 4 E2B, E4B, 12B, 26B A4B, and 31B.
> * **Mobile-optimized** (wNa8o8): A custom schema engineered explicitly for mobile hardware efficiency. It features targeted 2-bit decoding layers, optimized KV caches, and static activations to maximize VRAM savings. Available for Gemma 4 E2B and E4B.
> * **Compressed Tensors** (w4a16): QAT checkpoints serialized in the compressed-tensors format for native, optimized inference with vLLM. Available for Gemma 4 E2B, E4B, 12B
...
Repository: localaiLicense: apache-2.0
step-3.7-flash
**[ModelPage]**: https://static.stepfun.com/blog/step-3.7-flash/
## 1. Introduction
Step 3.7 Flash is a 198B-parameter sparse Mixture-of-Experts (MoE) vision-language model that combines a 196B-parameter language backbone with a 1.8B-parameter vision encoder for native image understanding. Engineered for high-frequency production workloads, it activates approximately 11B parameters per token and delivers a throughput of up to 400 tokens per second. Step 3.7 Flash supports a 256k context window and offers three selectable reasoning levels (low, medium, and high) so developers can easily balance speed, cost, and cognitive depth.
We built Step 3.7 Flash for developers who need to scale agentic workflows that combine perception, search, and reasoning. It is designed to handle intensive tasks such as parsing massive financial reports in one pass, running multi-step search loops with cross-source verification, or operating concurrent coding agents in high-throughput pipelines.
## 2. Capabilities & Performance
### Multimodal Perception and Verification
...
Repository: localaiLicense: apache-2.0
kimi-k2.6
🤗 huggingchat
|
📰 Tech Blog
## 1. Model Introduction
Kimi K2.6 is an open-source, native multimodal agentic model that advances practical capabilities in long-horizon coding, coding-driven design, proactive autonomous execution, and swarm-based task orchestration.
### Key Features
- **Long-Horizon Coding**: K2.6 achieves significant improvements on complex, end-to-end coding tasks, generalizing robustly across programming languages (Rust, Go, Python) and domains spanning front-end, DevOps, and performance optimization.
- **Coding-Driven Design**: K2.6 is capable of transforming simple prompts and visual inputs into production-ready interfaces and lightweight full-stack workflows, generating structured layouts, interactive elements, and rich animations with deliberate aesthetic precision.
- **Elevated Agent Swarm**: Scaling horizontally to 300 sub-agents executing 4,000 coordinated steps, K2.6 can dynamically decompose tasks into parallel, domain-specialized subtasks, delivering end-to-end outputs from documents to websites to spreadsheets in a single autonomous run.
- **Proactive & Open Orchestration**: For autonomous tasks, K2.6 demonstra
...
Repository: localaiLicense: modified-mit
nanbeige4.1-3b-q8
Nanbeige4.1-3B is built upon Nanbeige4-3B-Base and represents an enhanced iteration of our previous reasoning model, Nanbeige4-3B-Thinking-2511, achieved through further post-training optimization with supervised fine-tuning (SFT) and reinforcement learning (RL). As a highly competitive open-source model at a small parameter scale, Nanbeige4.1-3B illustrates that compact models can simultaneously achieve robust reasoning, preference alignment, and effective agentic behaviors.
Key features:
Strong Reasoning: Capable of solving complex, multi-step problems through sustained and coherent reasoning within a single forward pass, reliably producing correct answers on benchmarks like LiveCodeBench-Pro, IMO-Answer-Bench, and AIME 2026 I.
Robust Preference Alignment: Outperforms same-scale models (e.g., Qwen3-4B-2507, Nanbeige4-3B-2511) and larger models (e.g., Qwen3-30B-A3B, Qwen3-32B) on Arena-Hard-v2 and Multi-Challenge.
Agentic Capability: First general small model to natively support deep-search tasks and sustain complex problem-solving with >500 rounds of tool invocations; excels in benchmarks like xBench-DeepSearch (75), Browse-Comp (39), and others.
Repository: localaiLicense: apache-2.0
nanbeige4.1-3b-q4
Nanbeige4.1-3B is built upon Nanbeige4-3B-Base and represents an enhanced iteration of our previous reasoning model, Nanbeige4-3B-Thinking-2511, achieved through further post-training optimization with supervised fine-tuning (SFT) and reinforcement learning (RL). As a highly competitive open-source model at a small parameter scale, Nanbeige4.1-3B illustrates that compact models can simultaneously achieve robust reasoning, preference alignment, and effective agentic behaviors.
Key features:
Strong Reasoning: Capable of solving complex, multi-step problems through sustained and coherent reasoning within a single forward pass, reliably producing correct answers on benchmarks like LiveCodeBench-Pro, IMO-Answer-Bench, and AIME 2026 I.
Robust Preference Alignment: Outperforms same-scale models (e.g., Qwen3-4B-2507, Nanbeige4-3B-2511) and larger models (e.g., Qwen3-30B-A3B, Qwen3-32B) on Arena-Hard-v2 and Multi-Challenge.
Agentic Capability: First general small model to natively support deep-search tasks and sustain complex problem-solving with >500 rounds of tool invocations; excels in benchmarks like xBench-DeepSearch (75), Browse-Comp (39), and others.
Repository: localaiLicense: apache-2.0
vits-piper-it_IT-paola-sherpa
Italian (it_IT) single-speaker Piper VITS voice "paola" (medium quality, 22.05 kHz), served through the sherpa-onnx backend with native streaming TTS. Ships espeak-ng phonemization data, so it works for Italian out of the box.
Repository: localaiLicense: other
vits-piper-it_IT-dii-high-sherpa
Italian (it_IT) single-speaker Piper VITS voice "dii" (high quality, 22.05 kHz), served through the sherpa-onnx backend with native streaming TTS. Ships espeak-ng phonemization data. Non-commercial use only (CC BY-NC-SA 4.0).
Repository: localaiLicense: cc-by-nc-sa-4.0
vits-piper-it_IT-miro-high-sherpa
Italian (it_IT) single-speaker Piper VITS voice "miro" (high quality, 22.05 kHz), served through the sherpa-onnx backend with native streaming TTS. Ships espeak-ng phonemization data. Non-commercial use only (CC BY-NC-SA 4.0).
Repository: localaiLicense: cc-by-nc-sa-4.0
vits-piper-it_IT-riccardo-x_low-sherpa
Italian (it_IT) single-speaker Piper VITS voice "riccardo" (x-low quality, 16 kHz), served through the sherpa-onnx backend with native streaming TTS. Ships espeak-ng phonemization data.
Repository: localaiLicense: other
vits-piper-en_US-amy-sherpa
English (en_US) single-speaker Piper VITS voice "amy" (medium quality, 22.05 kHz), served through the sherpa-onnx backend with native streaming TTS. Ships espeak-ng phonemization data.
Repository: localaiLicense: other
vits-piper-es_ES-davefx-sherpa
Spanish (es_ES) single-speaker Piper VITS voice "davefx" (medium quality, 22.05 kHz), served through the sherpa-onnx backend with native streaming TTS. Ships espeak-ng phonemization data.
Repository: localaiLicense: cc0-1.0
vits-piper-fr_FR-siwis-sherpa
French (fr_FR) single-speaker Piper VITS voice "siwis" (medium quality, 22.05 kHz), served through the sherpa-onnx backend with native streaming TTS. Ships espeak-ng phonemization data.
Repository: localaiLicense: cc-by-4.0
vits-piper-de_DE-thorsten-sherpa
German (de_DE) single-speaker Piper VITS voice "thorsten" (medium quality, 22.05 kHz), served through the sherpa-onnx backend with native streaming TTS. Ships espeak-ng phonemization data.
Repository: localaiLicense: cc0-1.0
vits-piper-en_GB-alan-low-sherpa
English (en_GB) single-speaker Piper VITS voice "alan" (low quality, 16 kHz), served through the sherpa-onnx backend with native streaming TTS. Ships espeak-ng phonemization data.
Repository: localaiLicense: other
vits-piper-en_GB-alan-medium-sherpa
English (en_GB) single-speaker Piper VITS voice "alan" (medium quality, 22.05 kHz), served through the sherpa-onnx backend with native streaming TTS. Ships espeak-ng phonemization data.
Repository: localaiLicense: other
vits-piper-en_GB-alba-medium-sherpa
English (en_GB) single-speaker Piper VITS voice "alba" (medium quality, 22.05 kHz), served through the sherpa-onnx backend with native streaming TTS. Ships espeak-ng phonemization data.
Repository: localaiLicense: cc-by-4.0
vits-piper-en_GB-aru-medium-sherpa
English (en_GB) multi-speaker (12 voices) Piper VITS voice "aru" (medium quality, 22.05 kHz), served through the sherpa-onnx backend with native streaming TTS. Ships espeak-ng phonemization data. Pick a speaker with the numeric voice/speaker id.
Repository: localaiLicense: cc-by-4.0
vits-piper-en_GB-cori-high-sherpa
English (en_GB) single-speaker Piper VITS voice "cori" (high quality, 22.05 kHz), served through the sherpa-onnx backend with native streaming TTS. Ships espeak-ng phonemization data.
Repository: localaiLicense: cc0-1.0
vits-piper-en_GB-cori-medium-sherpa
English (en_GB) single-speaker Piper VITS voice "cori" (medium quality, 22.05 kHz), served through the sherpa-onnx backend with native streaming TTS. Ships espeak-ng phonemization data.
Repository: localaiLicense: cc0-1.0
Page
1
of many