Model Gallery

Qwen3-TTS 0.6B Custom Voice (C++ / GGML) — text-to-speech with voice cloning support. Generates 24kHz mono audio with optional reference audio for voice cloning via ECAPA-TDNN speaker embeddings. Supports 10 languages (en, zh, ja, ko, de, fr, es, it, pt, ru).

Links

• https://huggingface.co/endo5501/qwen3-tts.cpp
• https://github.com/predict-woo/qwen3-tts.cpp

**Model Name:** Qwen3-VL-Reranker-8B **Base Model:** Qwen/Qwen3-VL-Reranker-8B **Description:** A high-performance multimodal reranking model for state-of-the-art cross-modal search. It supports 30+ languages and handles text, images, screenshots, videos, and mixed modalities. With 8B parameters and a 32K context length, it refines retrieval results by combining embedding vectors with precise relevance scores. Optimized for efficiency, it supports quantized versions (e.g., Q8_0, Q4_K_M) and is ideal for applications requiring accurate multimodal content matching. **Key Features:** - **Multimodal**: Text, images, videos, and mixed content. - **Language Support**: 30+ languages. - **Quantization**: Available in Q8_0 (best quality), Q4_K_M (fast, recommended), and lower-precision options. - **Performance**: Outperforms base models in retrieval tasks (e.g., JinaVDR, ViDoRe v3). - **Use Case**: Enhances search pipelines by refining embeddings with precise relevance scores. **Downloads:** - [GGUF Files](https://huggingface.co/mradermacher/Qwen3-VL-Reranker-8B-GGUF) (e.g., `Qwen3-VL-Reranker-8B.Q8_0.gguf`). **Usage:** - Requires `transformers`, `qwen-vl-utils`, and `torch`. - Example: `from scripts.qwen3_vl_reranker import Qwen3VLReranker; model = Qwen3VLReranker(...)` **Citation:** @article{qwen3vlembedding, ...} This description emphasizes its capabilities, efficiency, and versatility for multimodal search tasks.

Links

• https://huggingface.co/mradermacher/Qwen3-VL-Reranker-8B-GGUF

**Model Name:** Qwen3-VL-Reranker-2B-i1 **Base Model:** Qwen/Qwen3-VL-Reranker-2B **Description:** A high-performance multimodal reranking model for state-of-the-art cross-modal search. It supports 30+ languages and handles text, images, screenshots, videos, and mixed modalities. With 8B parameters and a 32K context length, it refines retrieval results by combining embedding vectors with precise relevance scores. Optimized for efficiency, it supports quantized versions (e.g., Q8_0, Q4_K_M) and is ideal for applications requiring accurate multimodal content matching. **Key Features:** - **Multimodal**: Text, images, videos, and mixed content. - **Language Support**: 30+ languages. - **Quantization**: Available in Q8_0 (best quality), Q4_K_M (fast, recommended), and lower-precision options. - **Performance**: Outperforms base models in retrieval tasks (e.g., JinaVDR, ViDoRe v3). - **Use Case**: Enhances search pipelines by refining embeddings with precise relevance scores. **Downloads:** - [GGUF Files](https://huggingface.co/mradermacher/Qwen3-VL-Reranker-2B-i1-GGUF) (e.g., `Qwen3-VL-Reranker-2B.i1-Q4_K_M.gguf`). **Usage:** - Requires `transformers`, `qwen-vl-utils`, and `torch`. - Example: `from scripts.qwen3_vl_reranker import Qwen3VLReranker; model = Qwen3VLReranker(...)` **Citation:** @article{qwen3vlembedding, ...} This description emphasizes its capabilities, efficiency, and versatility for multimodal search tasks.

Links

• https://huggingface.co/mradermacher/Qwen3-VL-Reranker-2B-i1-GGUF

Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date. This generation delivers comprehensive upgrades across the board: superior text understanding & generation, deeper visual perception & reasoning, extended context length, enhanced spatial and video dynamics comprehension, and stronger agent interaction capabilities. Available in Dense and MoE architectures that scale from edge to cloud, with Instruct and reasoning‑enhanced Thinking editions for flexible, on-demand deployment. #### Key Enhancements: * **Visual Agent**: Operates PC/mobile GUIs—recognizes elements, understands functions, invokes tools, completes tasks. * **Visual Coding Boost**: Generates Draw.io/HTML/CSS/JS from images/videos. * **Advanced Spatial Perception**: Judges object positions, viewpoints, and occlusions; provides stronger 2D grounding and enables 3D grounding for spatial reasoning and embodied AI. * **Long Context & Video Understanding**: Native 256K context, expandable to 1M; handles books and hours-long video with full recall and second-level indexing. * **Enhanced Multimodal Reasoning**: Excels in STEM/Math—causal analysis and logical, evidence-based answers. * **Upgraded Visual Recognition**: Broader, higher-quality pretraining is able to “recognize everything”—celebrities, anime, products, landmarks, flora/fauna, etc. * **Expanded OCR**: Supports 32 languages (up from 19); robust in low light, blur, and tilt; better with rare/ancient characters and jargon; improved long-document structure parsing. * **Text Understanding on par with pure LLMs**: Seamless text–vision fusion for lossless, unified comprehension. #### Model Architecture Updates: 1. **Interleaved-MRoPE**: Full‑frequency allocation over time, width, and height via robust positional embeddings, enhancing long‑horizon video reasoning. 2. **DeepStack**: Fuses multi‑level ViT features to capture fine-grained details and sharpen image–text alignment. 3. **Text–Timestamp Alignment:** Moves beyond T‑RoPE to precise, timestamp‑grounded event localization for stronger video temporal modeling. This is the weight repository for Qwen3-VL-30B-A3B-Instruct.

Links

• https://huggingface.co/unsloth/Qwen3-VL-30B-A3B-Instruct-GGUF

AFM-4.5B is a 4.5 billion parameter instruction-tuned model developed by Arcee.ai, designed for enterprise-grade performance across diverse deployment environments from cloud to edge. The base model was trained on a dataset of 8 trillion tokens, comprising 6.5 trillion tokens of general pretraining data followed by 1.5 trillion tokens of midtraining data with enhanced focus on mathematical reasoning and code generation. Following pretraining, the model underwent supervised fine-tuning on high-quality instruction datasets. The instruction-tuned model was further refined through reinforcement learning on verifiable rewards as well as for human preference. We use a modified version of TorchTitan for pretraining, Axolotl for supervised fine-tuning, and a modified version of Verifiers for reinforcement learning. The development of AFM-4.5B prioritized data quality as a fundamental requirement for achieving robust model performance. We collaborated with DatologyAI, a company specializing in large-scale data curation. DatologyAI's curation pipeline integrates a suite of proprietary algorithms—model-based quality filtering, embedding-based curation, target distribution-matching, source mixing, and synthetic data. Their expertise enabled the creation of a curated dataset tailored to support strong real-world performance. The model architecture follows a standard transformer decoder-only design based on Vaswani et al., incorporating several key modifications for enhanced performance and efficiency. Notable architectural features include grouped query attention for improved inference efficiency and ReLU^2 activation functions instead of SwiGLU to enable sparsification while maintaining or exceeding performance benchmarks. The model available in this repo is the instruct model following supervised fine-tuning and reinforcement learning.

Links

• https://huggingface.co/arcee-ai/AFM-4.5B
• https://huggingface.co/bartowski/arcee-ai_AFM-4.5B-GGUF

Face recognition using insightface's `buffalo_l` pack (SCRFD-10GF detector + ResNet50 ArcFace 512-d embedder + genderage head, ~326MB). Default choice, highest accuracy. Weights delivered via LocalAI's gallery mechanism (SHA-256 verified, cached in the models directory like any other managed model). NON-COMMERCIAL RESEARCH USE ONLY. For commercial use see `insightface-opencv`.

Links

• https://github.com/deepinsight/insightface

Mid-tier insightface pack (SCRFD-2.5GF detector + ResNet50 ArcFace + genderage, ~313MB). Same recognition accuracy as `buffalo_l` with a cheaper detector — good balance on mid-range hardware. NON-COMMERCIAL RESEARCH USE ONLY.

Links

• https://github.com/deepinsight/insightface

Small insightface pack (SCRFD-500MF detector + MBF 512-d embedder + genderage, ~159MB). Good fit for mid-range CPU deployments. NON-COMMERCIAL RESEARCH USE ONLY.

Links

• https://github.com/deepinsight/insightface

Ultra-small insightface pack (SCRFD-500MF + MBF recognition only, ~16MB). NO landmarks, NO age/gender head — `/v1/face/analyze` returns empty attributes for this pack. Ideal for edge/embedded deployments where only verification and embedding are needed. NON-COMMERCIAL RESEARCH USE ONLY.

Links

• https://github.com/deepinsight/insightface

Largest insightface pack (SCRFD-10GF + ResNet100@Glint360K recognizer + genderage, ~407MB). Higher recognition accuracy than `buffalo_l` on harder benchmarks; pays for it in GPU memory. NON-COMMERCIAL RESEARCH USE ONLY.

Links

• https://github.com/deepinsight/insightface

Face recognition using OpenCV Zoo weights: YuNet detector + SFace 128-d recognizer (fp32). APACHE 2.0 — safe for commercial use. Lower accuracy than insightface packs, no demographic head (`/v1/face/analyze` returns detection regions only). Weights are downloaded on install via LocalAI's gallery mechanism (~40MB).

Links

• https://github.com/opencv/opencv_zoo

Int8-quantized OpenCV Zoo face pair (YuNet int8 + SFace int8, ~12MB). Roughly 3x smaller and noticeably faster on CPU than the fp32 variant at comparable accuracy for face tasks. APACHE 2.0 — commercial-safe. Weights are downloaded on install via LocalAI's gallery mechanism.

Links

• https://github.com/opencv/opencv_zoo

Speaker (voice) recognition with SpeechBrain's ECAPA-TDNN trained on VoxCeleb. 192-d L2-normalised embeddings, ~1.9% Equal Error Rate on VoxCeleb1-O. APACHE 2.0 — commercial-safe. The checkpoint is auto-downloaded from HuggingFace on first LoadModel (no separate weight file in gallery `files:`). Points at the upstream SpeechBrain HF repo directly — same bytes every deployment.

Links

• https://speechbrain.github.io/
• https://huggingface.co/speechbrain/spkrec-ecapa-voxceleb

Speaker recognition with WeSpeaker's ResNet34 trained on VoxCeleb, exported to ONNX. 256-d embeddings, CPU-friendly — avoids the PyTorch runtime entirely (onnxruntime only). APACHE 2.0. Pair with the `speaker-recognition` backend's OnnxDirectEngine. Use when ECAPA-TDNN's torch dependency is undesirable (small images, edge deployments).

Links

• https://github.com/wenet-e2e/wespeaker

The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B). This series inherits the exceptional multilingual capabilities, long-text understanding, and reasoning skills of its foundational model. The Qwen3 Embedding series represents significant advancements in multiple text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bitext mining. **Exceptional Versatility**: The embedding model has achieved state-of-the-art performance across a wide range of downstream application evaluations. The 8B size embedding model ranks No.1 in the MTEB multilingual leaderboard (as of June 5, 2025, score 70.58), while the reranking model excels in various text retrieval scenarios. **Comprehensive Flexibility**: The Qwen3 Embedding series offers a full spectrum of sizes (from 0.6B to 8B) for both embedding and reranking models, catering to diverse use cases that prioritize efficiency and effectiveness. Developers can seamlessly combine these two modules. Additionally, the embedding model allows for flexible vector definitions across all dimensions, and both embedding and reranking models support user-defined instructions to enhance performance for specific tasks, languages, or scenarios. **Multilingual Capability**: The Qwen3 Embedding series offer support for over 100 languages, thanks to the multilingual capabilites of Qwen3 models. This includes various programming languages, and provides robust multilingual, cross-lingual, and code retrieval capabilities. **Qwen3-Reranker-0.6B** has the following features: - Model Type: Text Reranking - Supported Languages: 100+ Languages - Number of Paramaters: 0.6B - Context Length: 32k - Quantization: q4_K_M, q5_0, q5_K_M, q6_K, q8_0, f16

Links

• https://huggingface.co/Qwen/Qwen3-Reranker-0.6B

The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B). This series inherits the exceptional multilingual capabilities, long-text understanding, and reasoning skills of its foundational model. The Qwen3 Embedding series represents significant advancements in multiple text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bitext mining. **Exceptional Versatility**: The embedding model has achieved state-of-the-art performance across a wide range of downstream application evaluations. The 8B size embedding model ranks **No.1** in the MTEB multilingual leaderboard (as of June 5, 2025, score **70.58**), while the reranking model excels in various text retrieval scenarios. **Comprehensive Flexibility**: The Qwen3 Embedding series offers a full spectrum of sizes (from 0.6B to 8B) for both embedding and reranking models, catering to diverse use cases that prioritize efficiency and effectiveness. Developers can seamlessly combine these two modules. Additionally, the embedding model allows for flexible vector definitions across all dimensions, and both embedding and reranking models support user-defined instructions to enhance performance for specific tasks, languages, or scenarios. **Multilingual Capability**: The Qwen3 Embedding series offer support for over 100 languages, thanks to the multilingual capabilites of Qwen3 models. This includes various programming languages, and provides robust multilingual, cross-lingual, and code retrieval capabilities. **Qwen3-Embedding-4B-GGUF** has the following features: - Model Type: Text Embedding - Supported Languages: 100+ Languages - Number of Paramaters: 4B - Context Length: 32k - Embedding Dimension: Up to 2560, supports user-defined output dimensions ranging from 32 to 2560 - Quantization: q4_K_M, q5_0, q5_K_M, q6_K, q8_0, f16

Links

• https://huggingface.co/Qwen/Qwen3-Embedding-4B-GGUF

The Qwen3 Embedding series model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B). This series inherits the exceptional multilingual capabilities, long-text understanding, and reasoning skills of its foundational model. The Qwen3 Embedding series represents significant advancements in multiple text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bitext mining. **Exceptional Versatility**: The embedding model has achieved state-of-the-art performance across a wide range of downstream application evaluations. The 8B size embedding model ranks **No.1** in the MTEB multilingual leaderboard (as of June 5, 2025, score **70.58**), while the reranking model excels in various text retrieval scenarios. **Comprehensive Flexibility**: The Qwen3 Embedding series offers a full spectrum of sizes (from 0.6B to 8B) for both embedding and reranking models, catering to diverse use cases that prioritize efficiency and effectiveness. Developers can seamlessly combine these two modules. Additionally, the embedding model allows for flexible vector definitions across all dimensions, and both embedding and reranking models support user-defined instructions to enhance performance for specific tasks, languages, or scenarios. **Multilingual Capability**: The Qwen3 Embedding series offer support for over 100 languages, thanks to the multilingual capabilites of Qwen3 models. This includes various programming languages, and provides robust multilingual, cross-lingual, and code retrieval capabilities. **Qwen3-Embedding-8B-GGUF** has the following features: - Model Type: Text Embedding - Supported Languages: 100+ Languages - Number of Paramaters: 8B - Context Length: 32k - Embedding Dimension: Up to 4096, supports user-defined output dimensions ranging from 32 to 4096 - Quantization: q4_K_M, q5_0, q5_K_M, q6_K, q8_0, f16

Links

• https://huggingface.co/Qwen/Qwen3-Embedding-8B-GGUF

The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B). This series inherits the exceptional multilingual capabilities, long-text understanding, and reasoning skills of its foundational model. The Qwen3 Embedding series represents significant advancements in multiple text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bitext mining. **Exceptional Versatility**: The embedding model has achieved state-of-the-art performance across a wide range of downstream application evaluations. The 8B size embedding model ranks **No.1** in the MTEB multilingual leaderboard (as of June 5, 2025, score **70.58**), while the reranking model excels in various text retrieval scenarios. **Comprehensive Flexibility**: The Qwen3 Embedding series offers a full spectrum of sizes (from 0.6B to 8B) for both embedding and reranking models, catering to diverse use cases that prioritize efficiency and effectiveness. Developers can seamlessly combine these two modules. Additionally, the embedding model allows for flexible vector definitions across all dimensions, and both embedding and reranking models support user-defined instructions to enhance performance for specific tasks, languages, or scenarios. **Multilingual Capability**: The Qwen3 Embedding series offer support for over 100 languages, thanks to the multilingual capabilites of Qwen3 models. This includes various programming languages, and provides robust multilingual, cross-lingual, and code retrieval capabilities. **Qwen3-Embedding-0.6B-GGUF** has the following features: - Model Type: Text Embedding - Supported Languages: 100+ Languages - Number of Paramaters: 0.6B - Context Length: 32k - Embedding Dimension: Up to 1024, supports user-defined output dimensions ranging from 32 to 1024 - Quantization: q8_0, f16

Links

• https://huggingface.co/Qwen/Qwen3-Embedding-0.6B-GGUF

This is a requantized version of https://huggingface.co/google/gemma-3-27b-it-qat-q4_0-gguf. The official QAT weights released by google use fp16 (instead of Q6_K) for the embeddings table, which makes this model take a significant extra amount of memory (and storage) compared to what Q4_0 quants are supposed to take. Requantizing with llama.cpp achieves a very similar result. Note that this model ends up smaller than the Q4_0 from Bartowski. This is because llama.cpp sets some tensors to Q4_1 when quantizing models to Q4_0 with imatrix, but this is a static quant. The perplexity score for this one is even lower with this model compared to the original model by Google, but the results are within margin of error, so it's probably just luck. I also fixed the control token metadata, which was slightly degrading the performance of the model in instruct mode.

Links

• https://huggingface.co/google/gemma-3-27b-it-qat-q4_0-gguf
• https://huggingface.co/stduhpf/google-gemma-3-27b-it-qat-q4_0-gguf-small

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.

Links

• https://huggingface.co/RWKV/rwkv-6-world-7b
• https://huggingface.co/bartowski/rwkv-6-world-7b-GGUF

Granite-Embedding-107M-Multilingual is a 107M parameter dense biencoder embedding model from the Granite Embeddings suite that can be used to generate high quality text embeddings. This model produces embedding vectors of size 384 and is trained using a combination of open source relevance-pair datasets with permissive, enterprise-friendly license, and IBM collected and generated datasets. This model is developed using contrastive finetuning, knowledge distillation and model merging for improved performance.

Links

• https://huggingface.co/ibm-granite/granite-embedding-107m-multilingual
• https://huggingface.co/bartowski/granite-embedding-107m-multilingual-GGUF