Filter by type:
Filter by tags:
gemmable-4-12b-mtp
## Gemmable 4 12B
Gemmable 4 12B is a GGUF export of Gemma 4 12B fine-tuned on Fable-5 style
reasoning and assistant traces.
## Highlights
- Base model: `google/gemma-4-12B`
- Format: GGUF
- Training style: Fable-5 style reasoning and assistant traces
- Distribution: fp16 GGUF plus matching assistant GGUFs for each quant
- Intended use: local inference, coding, reasoning, and assistant workflows
## How to use
### llama.cpp
Standard load:
```bash
llama-server -m "gemmable-4-12b-fp16.gguf"
```
Speculative / draft-MTP load:
```bash
llama-server -m "gemmable-4-12b-Q4_K_M.gguf" \
--spec-draft-model "gemmable-4-12b-Q4_K_M-mtp.gguf" \
--spec-type draft-mtp \
--spec-draft-n-max 4
```
Use the matching fp16 or quantized main file with its `-mtp` companion.
### LM Studio
1. Search this repo, download target + mtp file.
2. Load target.
3. Load settings → Speculative Decoding → select mtp file file.
(Requires LM Studio with am17an's PR merged or custom llama.cpp runtime. As of 2026-05, mainline LM Studio runtime doesn't yet have `draft-mtp` for Gemma-4 — track upstream merge.)
## GGUF / local inference notes
...
Repository: localai
lfm2.5-1.2b-instruct
Try LFM • Docs • LEAP • Discord
# LFM2.5-1.2B-Instruct
LFM2.5 is a new family of hybrid models designed for **on-device deployment**. It builds on the LFM2 architecture with extended pre-training and reinforcement learning.
- **Best-in-class performance**: A 1.2B model rivaling much larger models, bringing high-quality AI to your pocket.
- **Fast edge inference**: 239 tok/s decode on AMD CPU, 82 tok/s on mobile NPU. Runs under 1GB of memory with day-one support for llama.cpp, MLX, and vLLM.
- **Scaled training**: Extended pre-training from 10T to 28T tokens and large-scale multi-stage reinforcement learning.
Find more information about LFM2.5 in our blog post.
## 🗒️ Model Details
LFM2.5-1.2B-Instruct is a general-purpose text-only model with the following features:
...
Repository: localaiLicense: other
gemma-4-12b-agentic-fable5-composer2.5-v2-3.5x-tau2
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: apache-2.0
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-4-12b-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
gemma-4-e2b-it-qat-q4_0
Gemma 4 E2B is a multimodal (text + image) instruction-tuned model from Google DeepMind, optimized with Quantization-Aware Training (QAT) to preserve bfloat16-level quality at a fraction of the memory. E2B is a MatFormer "effective 2B" elastic variant: it carries a larger backbone but runs at an effective 2B-parameter footprint, making it well suited to lightweight and on-device deployments. This is the official Google Q4_0 GGUF, shipped with its multimodal projector.
License: Apache 2.0 | Authors: Google DeepMind
Repository: localaiLicense: apache-2.0
gemma-4-e2b-it
Google Gemma 4 E2B-IT is a lightweight open-source multimodal model with 5B total parameters and 2B effective parameters using selective parameter activation. It handles text and image input, generating text output, with a 256K context window and support for 140+ languages. Optimized for efficient execution on low-resource devices including mobile and laptops.
Repository: localaiLicense: apache-2.0
qwen_qwen3.5-2b
Qwen3.5-2B is a highly efficient, instruction-tuned multilingual language model available in various quantized GGUF formats. Optimized for llama-cpp inference, it supports chat and completion tasks with strong performance on low-RAM hardware. The model is available in multiple quantization levels ranging from Q8_0 to IQ2_M to balance quality and resource usage.
Repository: localaiLicense: apache-2.0
qwen3.5-122b-a10b
Repository: localaiLicense: apache-2.0
qwen3-vl-embedding-2b
**Model Name:** Qwen3-VL-Embedding-2B
**Base Model:** Qwen/Qwen3-VL-2B-Instruct
**Description:**
The **Qwen3-VL-Embedding** and **Qwen3-VL-Reranker** model series are the latest additions to the Qwen family, built upon the recently open-sourced and powerful Qwen3-VL foundation model. Specifically designed for multimodal information retrieval and cross-modal understanding, this suite accepts diverse inputs including text, images, screenshots, and videos, as well as inputs containing a mixture of these modalities.
**Key Features:**
- Model Type: MultiModal Embedding
- Supported Languages: 30+ Languages
- Supported Input Modalities: Text, images, screenshots, videos, and arbitrary multimodal combinations (e.g., text + image, text + video)
- Number of Parameters: 2B
- Context Length: 32k
- Embedding Dimension: Up to 2048, supports user-defined output dimensions ranging from 64 to 2048
**Downloads:**
- [GGUF Files](https://huggingface.co/Qwen/Qwen3-VL-Embedding-2B) (e.g., `Qwen3-VL-Embedding-2B-Q8_0.gguf`).
**Usage:**
- Requires `transformers`, `qwen-vl-utils`, and `torch`.
- Example: `from scripts.qwen3_vl_embedding import Qwen3VLEmbedder model = Qwen3VLEmbedder(...)`
**Citation:**
@article{qwen3vlembedding, ...}
This description emphasizes its capabilities, efficiency, and versatility for multimodal search tasks.
Repository: localaiLicense: apache-2.0
qwen3-vl-reranker-2b-i1
**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.
Repository: localaiLicense: apache-2.0
lfm2.5-1.2b-nova-function-calling
The **LFM2.5-1.2B-Nova-Function-Calling-GGUF** is a quantized version of the original model, optimized for efficiency with **Unsloth**. It supports text and multimodal tasks, using different quantization levels (e.g., Q2_K, Q3_K, Q4_K, etc.) to balance performance and memory usage. The model is designed for function calling and is faster than the original version, making it suitable for tasks like code generation, reasoning, and multi-modal input processing.
Repository: localaiLicense: apache-2.0
mistral-nemo-instruct-2407-12b-thinking-m-claude-opus-high-reasoning-i1
The model described in this repository is the **Mistral-Nemo-Instruct-2407-12B** (12 billion parameters), a large language model optimized for instruction tuning and high-level reasoning tasks. It is a **quantized version** of the original model, compressed for efficiency while retaining key capabilities. The model is designed to generate human-like text, perform complex reasoning, and support multi-modal tasks, making it suitable for applications requiring strong language understanding and output.
Repository: localai
allenai_olmo-3.1-32b-think
The **Olmo-3.1-32B-Think** model is a large language model (LLM) optimized for efficient inference using quantized versions. It is a quantized version of the original **allenai/Olmo-3.1-32B-Think** model, developed by **bartowski** using the **imatrix** quantization method.
### Key Features:
- **Base Model**: `allenai/Olmo-3.1-32B-Think` (unquantized version).
- **Quantized Versions**: Available in multiple formats (e.g., `Q6_K_L`, `Q4_1`, `bf16`) with varying precision (e.g., Q8_0, Q6_K_L, Q5_K_M). These are derived from the original model using the **imatrix calibration dataset**.
- **Performance**: Optimized for low-memory usage and efficient inference on GPUs/CPUs. Recommended quantization types include `Q6_K_L` (near-perfect quality) or `Q4_K_M` (default, balanced performance).
- **Downloads**: Available via Hugging Face CLI. Split into multiple files if needed for large models.
- **License**: Apache-2.0.
### Recommended Quantization:
- Use `Q6_K_L` for highest quality (near-perfect performance).
- Use `Q4_K_M` for balanced performance and size.
- Avoid lower-quality options (e.g., `Q3_K_S`) unless specific hardware constraints apply.
This model is ideal for deploying on GPUs/CPUs with limited memory, leveraging efficient quantization for practical use cases.
Repository: localaiLicense: apache-2.0
qwen3-vl-32b-instruct
Qwen3-VL-32B-Instruct is the 32B parameter model of the Qwen3-VL series.
Repository: localaiLicense: apache-2.0
qwen3-vl-2b-thinking
Qwen3-VL-2B-Thinking is the 2B parameter model of the Qwen3-VL series that is thinking.
Repository: localaiLicense: apache-2.0
qwen3-vl-2b-instruct
Qwen3-VL-2B-Instruct is the 2B parameter model of the Qwen3-VL series.
Repository: localaiLicense: apache-2.0
ibm-granite_granite-4.0-h-small
Granite-4.0-H-Small is a 32B parameter long-context instruct model finetuned from Granite-4.0-H-Small-Base using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets. This model is developed using a diverse set of techniques with a structured chat format, including supervised finetuning, model alignment using reinforcement learning, and model merging. Granite 4.0 instruct models feature improved instruction following (IF) and tool-calling capabilities, making them more effective in enterprise applications.
Repository: localaiLicense: apache-2.0
opengvlab_internvl3_5-2b
We introduce InternVL3.5, a new family of open-source multimodal models that significantly advances versatility, reasoning capability, and inference efficiency along the InternVL series. A key innovation is the Cascade Reinforcement Learning (Cascade RL) framework, which enhances reasoning through a two-stage process: offline RL for stable convergence and online RL for refined alignment. This coarse-to-fine training strategy leads to substantial improvements on downstream reasoning tasks, e.g., MMMU and MathVista. To optimize efficiency, we propose a Visual Resolution Router (ViR) that dynamically adjusts the resolution of visual tokens without compromising performance. Coupled with ViR, our Decoupled Vision-Language Deployment (DvD) strategy separates the vision encoder and language model across different GPUs, effectively balancing computational load. These contributions collectively enable InternVL3.5 to achieve up to a +16.0% gain in overall reasoning performance and a 4.05 ×\times× inference speedup compared to its predecessor, i.e., InternVL3. In addition, InternVL3.5 supports novel capabilities such as GUI interaction and embodied agency. Notably, our largest model, i.e., InternVL3.5-241B-A28B, attains state-of-the-art results among open-source MLLMs across general multimodal, reasoning, text, and agentic tasks—narrowing the performance gap with leading commercial models like GPT-5. All models and code are publicly released.
Repository: localaiLicense: apache-2.0
lfm2-1.2b
LFM2-1.2B is a hybrid liquid model designed for edge AI and on-device deployment, offering fast inference and multilingual support across 8 languages. It's optimized for agentic tasks, data extraction, and multi-turn conversations with efficient CPU/GPU/NPU compatibility.
Repository: localaiLicense: lfm1.0
liquidai_lfm2-1.2b-extract
Based on LFM2-1.2B, LFM2-1.2B-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.
Repository: localaiLicense: lfm1.0
Page 1