全站搜索
AI 模型 85012
- Supertonic-3-CoreML↗
aufklarer
**First-party CoreML export** of Supertonic-3's four non-autoregressive flow-matching graphs, for on-device iOS / Apple Neural Engine. Built by our own pipeline (`speech-models/stmodels`): weights lifted from the `Supertone/supertonic-3` ONNX initializers → PyTorch `nn.Module` → `coremltools` (`mlprogram`, FP32, iOS18+). Text/duration use **fixed T=128** (relpos attention has T-dependent pad widths — pad/segment text to 128); vocoder + vector-estimator use a dynamic latent-length `RangeDim`. The host runs the flow-matching ODE loop (`vector_estimator` ×`total_steps`) — the graphs contain no control flow. Assets to drive them: `tts.json`, `unicode_indexer.json` (G2P-free tokenizer table), `voice_styles/*.json`. > FP32 = parity reference. For **ANE residency**, use the mixed-precision > `Supertonic-3-CoreML-FP16` — vocoder + duration FP16, > text-encoder + vector-estimator FP32; measured transparent at **47–51 dB** mag-STFT SNR.
- Qwen3.8-27B-AWQ-4bit↗
barrydeen
AWQ **W4A16** quantization of `Qwen/Qwen3.8-27B`, produced with llm-compressor in `compressed-tensors` `pack-quantized` format — the best-optimised Marlin path on Ampere (SM 8.6). Qwen3.8-27B is a **hybrid** model. Only **16 of its 64** decoder layers use full attention; the other **48 use Gated DeltaNet** (`linear_attn.*`). Those DeltaNet projections are extremely sensitive to quantization, so they are left at full BF16 precision here, along with the vision tower and the multi-token-prediction head. That means only **256 Linear modules** are quantized — 16 layers × 4 attention projections plus 64 layers × 3 MLP projections — rather than the ~448 you would get by assuming a uniform architecture. Keeping 48 layers of DeltaNet in BF16 costs roughly 7 GB versus builds that quantize everything, and that is the entire difference in file size.
- Hubble-4B-v1-GGUF↗
bartowski
- nvidia_Llama-3.1-8B-UltraLong-1M-Instruct-GGUF↗
bartowski
- p-e-w_phi-4-heretic-GGUF↗
bartowski
- TheDrummer_Cydonia-24B-v4.2.0-GGUF↗
bartowski
All quants made using imatrix option with dataset from here combined with a subset of combined_all_small.parquet from Ed Addario here No chat template specified so default is used. This may be incorrect, check original model card for details. Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.
- flux.1-dev-uncensored-q4↗
BaZzzuka
- ESMC-600M-step250k↗
biohub
- Desearch-Embedding-4B↗
desearch
- MiniCPM5-2B-Abliterated-iq4XS-GGUF↗
edgebites
