Filter by type:
Filter by tags:
qwen3.8-2b-q4
Qwen3.8-2B is Empero AI's smallest Qwen3.8 reasoning distillation. It uses
the Qwen3.5-2B architecture and targets mathematics, instruction
following, tool use, and edge deployment with a native 262K-token context
window. This default entry uses Q4_K_M weights; a higher-quality Q8_0
build is available as a variant.
Repository: localaiLicense: apache-2.0
qwen3.8-2b-q8
Qwen3.8-2B in the higher-quality Q8_0 GGUF format. This variant preserves
more model fidelity while remaining suitable for compact hosts.
Repository: localaiLicense: apache-2.0
mellum2-12b-a2.5b-instruct
Mellum2-12B-A2.5B-Instruct is an Apache-2.0 mixture-of-experts model from
JetBrains with 12 billion total parameters, 2.5 billion activated per token,
and a 131,072-token context window.
This entry uses the Q4_K_M GGUF quantization.
Repository: localaiLicense: apache-2.0
mellum2-12b-a2.5b-instruct-q8
Mellum2-12B-A2.5B-Instruct is an Apache-2.0 mixture-of-experts model from
JetBrains with 12 billion total parameters, 2.5 billion activated per token,
and a 131,072-token context window.
This entry uses the higher-quality Q8_0 GGUF quantization.
Repository: localaiLicense: apache-2.0
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 a llama.cpp runtime with Gemma 4 MTP support from ggml-org/llama.cpp#23398. LocalAI's pinned llama.cpp backend already carries it, so this entry runs draft-mtp out of the box.)
## 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
grug-12b
Grug 12B is kai-os's compact-reasoning fine-tune of Gemma 4 12B IT. It
targets shorter, denser reasoning traces while preserving constraints,
branching decisions, edge cases, and final-answer checks. This entry uses
Bartowski's Q4_K_M quantization and includes the multimodal projector for
Gemma 4 image inputs.
The model is experimental and its reported evaluation is a small local
math proxy rather than a broad benchmark. Review the upstream model card's
dataset provenance and `other` license before commercial or sensitive use.
Repository: localaiLicense: other
grug-12b-q8
Grug 12B is kai-os's compact-reasoning fine-tune of Gemma 4 12B IT. This
high-quality variant uses Bartowski's Q8_0 quantization and includes the
multimodal projector for Gemma 4 image inputs.
The model is experimental and its reported evaluation is a small local
math proxy rather than a broad benchmark. Review the upstream model card's
dataset provenance and `other` license before commercial or sensitive use.
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-agentic-fable5-composer2.5-v2-3.5x-tau2-mtp
Gemma 4 12B Agentic v2 is an Apache-2.0 fine-tune for coding, terminal
work, multi-step tool use, and reasoning. This variant pairs the Q4_K_M
target with the upstream Q8_0 Gemma 4 MTP drafter for faster lossless
generation through llama.cpp speculative decoding.
Repository: localaiLicense: apache-2.0
gemma-4-12b-agentic-fable5-composer2.5-v2-3.5x-tau2-q8
Gemma 4 12B Agentic v2 is an Apache-2.0 fine-tune for coding, terminal
work, multi-step tool use, and reasoning. This variant uses the
near-lossless Q8_0 GGUF quantization for higher output fidelity.
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-qat-mtp
Gemma 4 E2B IT QAT (Google DeepMind) paired with its Multi-Token Prediction (MTP) drafter head for speculative decoding on the llama.cpp backend. The Q4_K_XL target carries the full multimodal (text + image) model; the small `mtp-gemma-4-E2B-it` head predicts several tokens ahead which the target verifies in parallel, accelerating generation with no change to output quality. E2B is a MatFormer "effective 2B" elastic variant, well suited to lightweight and on-device deployments.
The drafter is not a standalone chat model: it only runs paired with the target, which is why both are bundled here. It uses the upstream `gemma4-assistant` architecture registered by llama.cpp PR #23398, so it loads on stock llama.cpp without any patch.
License: Apache 2.0 | Authors: Google DeepMind (target/drafter checkpoints), Unsloth (GGUF conversion)
Repository: localaiLicense: apache-2.0
gemma-4-12b-it-qat-mtp
Gemma 4 12B IT QAT (Google DeepMind) paired with its Multi-Token Prediction (MTP) drafter head for speculative decoding on the llama.cpp backend. The Q4_K_XL target carries the full multimodal (text + image) model; the small `mtp-gemma-4-12B-it` head predicts several tokens ahead which the target verifies in parallel, accelerating generation with no change to output quality. As a dense model, Gemma 4 12B is among the sizes that benefit most from MTP, with the llama.cpp PR reporting well over 1.4x decode speedup.
The drafter is not a standalone chat model: it only runs paired with the target, which is why both are bundled here. It uses the upstream `gemma4-assistant` architecture registered by llama.cpp PR #23398, so it loads on stock llama.cpp without any patch.
License: Apache 2.0 | Authors: Google DeepMind (target/drafter checkpoints), Unsloth (GGUF conversion)
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
Page 1