전체 검색
AI 모델 2119
- sam-vit-tiny-random↗
optimum-intel-internal-testing
- Qwen3.8-Flash-Next-REAP-288-MLX-4bit↗
sh0wie
Qwen3.8-Flash-Next with 288 of 512 experts per MoE layer, pruned with REAP saliency calibrated on the quantized weights, on the machine that serves them. It is a 180B-class MoE that runs on a 128 GB Mac for Claude Code-style agentic workloads and scores 91.5% on HumanEval. Decode is runtime-dependent: ~28 tok/s on stock mlx-vlm today, and 37 to 65 tok/s on the pmlx engine that ships with the tiered release (see "Decode speed" for the full breakdown). It supports MTP speculative decoding out of the box. Resident memory is ~68 GB as shipped, or ~39 GB when the n-gram table is streamed from NVMe (see "Running it"). For the ~39 GB streamed footprint, run under omlx v0.6.4 or newer. omlx offloads the n-gram table to NVMe automatically when the full model would not fit under the memory ceiling, so the build serves in about 39 GB resident. mlx-vlm runs the same build today at about 68 GB resident, with the n-gram table in memory. It streams to about 39 GB once PR #2045 (external PLE storage) lands in a release, since this repo already ships the `ple-store.json` manifest and `ple_storage` config that path reads. mlx-vlm needs `qwen4_exp` MTP support (git main after 2026-08-27, or any release that includes it):
- Qwen3-30B-A3B-GGUF↗
6block
All quants made using the imatrix option with a bilingual (English + Chinese) and code-heavy calibration dataset, so low-bit quants keep more of their Chinese and coding ability than a English-only calibration would. The `.imatrix` file used to produce these quants is included in this repo, so anyone can reproduce or extend the quant set with the exact same importance matrix. The first thing to figure out is how big a model you can run. For that you need to know how much RAM and/or VRAM you have.
- SNEX-V1↗
gbuzhf
**SNEX-V1 is Sage-A1.5 with a small, sparse transplant of Nex-N2.5-mini's training.** Sage is the body; from Nex only the largest changes its own training made are carried over, at a quarter of their strength. Everything else is Sage's: the vision projector, the MTP draft head, the router, the norms, the embeddings. Score: BF16 = 100; 70 % full-distribution fidelity `1/(1+KLD)` + 30 % same-top-1, averaged over the three sets. **1. Lineage first.** Weight comparisons placed the three models: Sage-A1.5 is a fine-tune of Qwen3.6-35B-A3B; Nex-N2.5-mini is a fine-tune of Qwen3.5-35B-A3B; Qwen3.6 continues Qwen3.5. So Nex's own training is `τ = Nex − Qwen3.5`. Taking the difference against Qwen3.6 instead would also subtract the 3.5 → 3.6 upgrade that Sage already carries.
- gguf-scanner-test-samples↗
dyingc
- pythia-160m↗
EleutherAI
The *Pythia Scaling Suite* is a collection of models developed to facilitate interpretability research (see paper). It contains two sets of eight models of sizes 70M, 160M, 410M, 1B, 1.4B, 2.8B, 6.9B, and 12B. For each size, there are two models: one trained on the Pile, and one trained on the Pile after the dataset has been globally deduplicated. All 8 model sizes are trained on the exact same data, in the exact same order. We also provide 154 intermediate checkpoints per model, hosted on Hugging Face as branches. The Pythia model suite was deliberately designed to promote scientific research on large language models, especially interpretability research. Despite not centering downstream performance as a design goal, we find the models match or exceed the performance of similar and same-sized models, such as those in the OPT and GPT-Neo suites. Previously, we released an early version of the Pythia suite to the public. However, we decided to retrain the model suite to address a few hyperparameter discrepancies. This model card lists the changes ; see appendix B in the Pythia paper for further discussion. We found no difference in benchmark performance between the two Pythia versions. The old models are still available, but we suggest the retrained suite if you are just starting to use Pythia. **This is the current release.**
- mask2former-swin-tiny-coco-instance↗
facebook
Mask2Former model trained on COCO instance segmentation (tiny-sized version, Swin backbone). It was introduced in the paper Masked-attention Mask Transformer for Universal Image Segmentation and first released in this repository. Disclaimer: The team releasing Mask2Former did not write a model card for this model so this model card has been written by the Hugging Face team. Mask2Former addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding labels. Hence, all 3 tasks are treated as if they were instance segmentation. Mask2Former outperforms the previous SOTA, MaskFormer both in terms of performance an efficiency by (i) replacing the pixel decoder with a more advanced multi-scale deformable attention Transformer, (ii) adopting a Transformer decoder with masked attention to boost performance without without introducing additional computation and (iii) improving training efficiency by calculating the loss on subsampled points instead of whole masks.
- sfm_unfiltered_e2e_alignment_upsampled_base↗
geodesic-research
- gemma-4-E2B-it-qat-q4_0-unquantized↗
Google
> [!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, and 31B. > * **Assistant Compatibility**: When using multi-token prediction (speculative decoding) with an assistant model alongside a QAT target model, the assistant model must also be a QAT checkpoint with the same precision to ensure compatibility. 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. Featuring both Dense and Mixture-of-Experts (MoE) architectures, Gemma 4 is well-suited for tasks like text generation, coding, and reasoning. The models are available in five distinct sizes: **E2B**, **E4B**, **12B**, **26B A4B**, and **31B**. Their diverse sizes make them deployable in environments ranging from high-end phones to laptops and servers, democratizing access to state-of-the-art AI.
- Qwen-Image-Edit-2509-GGUF↗
QuantStack
This GGUF file is a direct conversion of Qwen/Qwen-Image-Edit-2509 Type | Name | Location | Download | ------------ | -------------------------------------------------- | --------------------------------- | ------------------------- | Main Model | Qwen-Image | `ComfyUI/models/unet` | GGUF (this repo) | Main Text Encoder | Qwen2.5-VL-7B | `ComfyUI/models/text_encoders` | Safetensors / GGUF | | Text_Encoder (mmproj) | Qwen2.5-VL-7B-Instruct-mmproj-BF16 | `ComfyUI/models/text_encoders` (same folder as your main text encoder) | GGUF (this repo) | VAE | Qwen-Image VAE | `ComfyUI/models/vae` | Safetensors (this repo) | Since this is a quantized model, all original licensing terms and usage restrictions remain in effect.