전체 검색
AI 모델 2119
- MiniMax-H3-x-Z-Image-native↗
joeygambino
The comfy-native cuts of the MiniMax-H3 × Z-Image graft: Z-Image's spatial-attention profile on H3's engine — richer sets and textures, same identity, no per-shot sharpening creep. Full story, demos and verification on the GGUF page. Load with the plain **Load Diffusion Model** node, ComfyUI 0.32+. Files are the `pruned` H3 builds with the graft baked in (`zs05` = late-block gains, dose 0.5): - `bf16` — the master (ref2va) - `comfy-fp8` / `fp8e5m2` — fp8 scaled - `comfy-int8` / `int8_convrot` — the fast pick on RTX 50 - `comfy-w4a8` / `w4a4` / `nvfp4` — 4-bit family for 16 GB cards (`w4a8` is the quality pick; `nvfp4` is Blackwell-native, emulated elsewhere) - `comfy-mxfp8` — 8-bit microscaling, Blackwell-specialized; little benefit on older architectures - fl2va and ref2va variants where both exist; picking rules are identical to stock H3
- DeepSeek-V4-Flash-0731-bf16↗
PrimeIntellect
A bfloat16 re-export of deepseek-ai/DeepSeek-V4-Flash-0731. The weights are the published ones, dequantized: the dense linears from fp8 (e4m3 with ue8m0 scales over 128x128 blocks) and the routed experts from MXFP4, both to plain bfloat16. 43 layers, 114 safetensors shards. The upstream `config.json` carries `quantization_config` and `expert_dtype = "fp4"`. An inference engine reading those fields allocates fp8 linear parameters and MXFP4 expert parameters, which bfloat16 weights cannot fill. The routed experts at least fail loudly, in vLLM's `_load_w13`, where the packed MXFP4 shape does not match. The fp8 linears fail silently: a bfloat16 tensor has the same shape as the fp8 parameter it is loaded into, so `copy_` casts it elementwise and no dequantization scale is ever applied. Serving bfloat16 weights therefore requires a checkpoint whose config carries neither field, which is what this repo is. There is no Jinja chat template, by upstream design. Use the bundled `encoding/` directory, which is copied verbatim from upstream and is the reference implementation for turning OpenAI-format messages into an input string and for parsing completions back.
- Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-TTQ-GGUF↗
TokenTinkerer
**TTQ** (TokenTinkerer Quant) is a ten-rung GGUF ladder built from HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive, from 3.33 bpw to 6.72 bpw. Every rung was measured on the same machine, with the same protocol, against the same reference — and every claim below is a measurement, not an estimate. > **Source caveat — there is no full-precision release of this model.** The fine-tune is published > **only as GGUF**; no F16/BF16 weights exist. The highest-quality source available is therefore > upstream's `Q8_K_P` (~10 bpw), and it serves as **both** the requantization source for every rung > here **and** the reference against which all KLD / RMS figures are measured. Two consequences: > every quality number below is relative to *that file* rather than to the true full-precision > model, and an unknown fraction of each measured divergence is inherited from it and cannot be > separated without a full-precision source. Comparisons *between* files remain valid, because they > all share the same reference. The full-precision `Qwen/Qwen3.6-35B-A3B` base model is not a > substitute — the fine-tune is a different model. The point of the set is **efficiency at a given size**, and it holds two ways. Every rung beats the base repository's **nearest-size** quant on KLD — by **1.26× to 3.51×**. And every rung's **nearest-quality** partner there is a **1.44 to 7.90 GiB larger file**. The matched pairings below are also faster: **+6% to +19% decode**, **+28% to +80% prefill**. All with significance shown.
- pplx-computer-qwen-3-8-27b-mlx-20260824↗
perplexity-ai
MLX 4-bit build of the `qwen3.8_27b_rft_sdpo_10kdata_tools_88` RFT checkpoint (Qwen3.8-27B, RFT/SDPO tools post-training) — the same weights as `perplexity-ai/pplx-computer-qwen-3-8-27b-dflash2-20260824` (NVFP4), converted here from the original **bf16** checkpoint, not from the NVFP4 quant.
- sec-bert-base↗
nlpaueb
SEC-BERT is a family of BERT models for the financial domain, intended to assist financial NLP research and FinTech applications. SEC-BERT consists of the following models: * **SEC-BERT-BASE** (this model): Same architecture as BERT-BASE trained on financial documents. * **SEC-BERT-NUM**: Same as SEC-BERT-BASE but we replace every number token with a [NUM] pseudo-token handling all numeric expressions in a uniform manner, disallowing their fragmentation * **SEC-BERT-SHAPE**: Same as SEC-BERT-BASE but we replace numbers with pseudo-tokens that represent the number’s shape, so numeric expressions (of known shapes) are no longer fragmented, e.g., '53.2' becomes '[XX.X]' and '40,200.5' becomes '[XX,XXX.X]'. The model was pre-trained on 260,773 10-K filings from 1993-2019, publicly available at U.S. Securities and Exchange Commission (SEC) * We created a new vocabulary of 30k subwords by training a BertWordPieceTokenizer from scratch on the pre-training corpus. * We trained BERT using the official code provided in Google BERT's GitHub repository . * We then used Hugging Face's Transformers conversion script to convert the TF checkpoint in the desired format in order to be able to load the model in two lines of code for both PyTorch and TF2 users. * We release a model similar to the English BERT-BASE model (12-layer, 768-hidden, 12-heads, 110M parameters). * We chose to follow the same training set-up: 1 million training steps with batches of 256 sequences of length 512 with an initial learning rate 1e-4. * We were able to use a single Google Cloud TPU v3-8 provided for free from TensorFlow Research Cloud (TRC), while also utilizing GCP research credits. Huge thanks to both Google programs for supporting us!
- KAT-Coder-V2.5-Dev-MTP-GGUF↗
gbuzhf
KAT ships **`mtp_num_hidden_layers: 0`** — no draft head. These builds graft Qwen3.6-35B-A3B's **original** MTP head onto KAT's trunk, quantized with an imatrix calibrated on KAT's own output. Includes the **bf16 master** so you can build any tier yourself without a 69 GB safetensors pull or a conversion. We fine-tuned this head twice on KAT's own rollouts. **Both fine-tunes made it worse.** Measured live on 79 configs, same tier, same flags, only the head differing:
- indobert-base-p1↗
indobenchmark
IndoBERT was trained and evaluated by Bryan Wilie\*, Karissa Vincentio\*, Genta Indra Winata\*, Samuel Cahyawijaya\*, Xiaohong Li, Zhi Yuan Lim, Sidik Soleman, Rahmad Mahendra, Pascale Fung, Syafri Bahar, Ayu Purwarianti.
- stable-diffusion-inpainting↗
stable-diffusion-v1-5
Stable Diffusion Inpainting is a latent text-to-image diffusion model capable of generating photo-realistic images given any text input, with the extra capability of inpainting the pictures by using a mask. The **Stable-Diffusion-Inpainting** was initialized with the weights of the Stable-Diffusion-v-1-2. First 595k steps regular training, then 440k steps of inpainting training at resolution 512x512 on “laion-aesthetics v2 5+” and 10% dropping of the text-conditioning to improve classifier-free classifier-free guidance sampling. For inpainting, the UNet has 5 additional input channels (4 for the encoded masked-image and 1 for the mask itself) whose weights were zero-initialized after restoring the non-inpainting checkpoint. During training, we generate synthetic masks and in 25% mask everything. You can use this both with the 🧨Diffusers library and RunwayML GitHub repository ( now deprecated ), Automatic1111 .
- KVAE-3D-2.0-t4s16↗
kandinskylab
KVAE-Video 2.0 t4s16 is the higher-compression 4 x 16 x 16 video tokenizer in the KVAE 2.0 family. It is designed to provide the latent space for diffusion models, encoding videos into continuous 64-channel representations and reconstructing them with high fidelity. Its causal, fully convolutional architecture supports long videos through segment-wise processing with temporal caching. Run from the KVAE source repository root. The reference environment uses Python 3.11, PyTorch 2.8.0, and CUDA 12.8. Temporal segments are processed through internal block caches. Do not interleave independent videos on the same model instance; use one `KVAEVideo` instance per concurrent stream.
- llama-3-8b-samantha-i1-GGUF↗
mradermacher