全站搜索
AI 模型 84762
- Meta-Llama-3.1-8B-Instruct-GGUF↗
second-state
- Qwen3.8-27B-GPTQ-Int4-sym-G128-MTP-BF16↗
SergiioB
Self-quantized on the target GPU (gptqmodel 7.3.2) for **vLLM XPU serving on Intel Arc (Xe2)**. The single MTP draft layer is deliberately **excluded from quantization and kept in BF16**, so native speculative decoding (MTP) works out of the box — and an optional **runtime INT4 draft overlay** (below) takes single-stream decode from **83.7 → 112.7 tok/s** on the same checkpoint. > All numbers are **real measurements** taken on a single Intel Arc Pro B70 > 32 GB — client-side timing, n=5 medians, 230 W cap, context 131072, fp8 KV, > served at the Qwen3.8-27B model card's recommended sampling — > **non-thinking: temperature 0.7, top_p 0.80, top_k 20, presence_penalty 1.5** > (thinking: 1.0 / 0.95 / 20). Greedy rows are marked greedy. > Commands, methodology and raw logs are public: 📖 > **Intel Arc Pro B70 Inference Cookbook** (see the link section below). - **Repo:** intel-arc-pro-b70-inference-cookbook - **This model's recipe:** QWEN38-VLLM-XPU.md - **INT4 draft overlay:** DRAFT-INT4-S-M1.md - **Copy-paste launch lines:** FULL-SETUP-COMMANDS.md - **Image + patch matrix:** IMAGE-AND-PATCH-MATRIX.md
- Qwen3.8-9B-Distill-AWQ-W4A16↗
Sohailhosseini
- SoulX-FlashTalk-14B↗
Soul-AILab
SoulX-FlashTalk: Real-Time Infinite Streaming of Audio-Driven Avatars via Self-Correcting Bidirectional Distillation - **2026.01.08** - We have released the inference code, and the model weights. - **2025.12.30** - We released **Project page** on SoulX-FlashTalk. - **2025.12.30** - We released **SoulX-FlashTalk Technical Report** on Arxiv and GitHub repository. **A 4-GPU version of SoulX-FlashTalk and a new open-source real-time streaming digital human model designed specifically for consumer-grade GPUs like 4090 etc.**
- Spark-X2.5-4B-Heretic-jp-gguf↗
soyaakinohara
GGUF quants of a Japanese-adapted, refusal-attenuated derivative of the XHToken/Spark-X2.5-4B model. The pipeline is: Heretic refusal attenuation → Japanese continued pretraining → Japanese instruction tuning → tool-calling repair. This release includes all four stages. A Spark-compatible llama.cpp fork is required (upstream does not support this architecture). Use XHToken/llama.cpp. Single-turn CLI example:
- gemma-4-31B-it-heretic-Gguf↗
Stabhappy
- hubert-large-superb-er↗
superb
The base model is hubert-large-ll60k, which is pretrained on 16kHz sampled speech audio. When using the model make sure that your speech input is also sampled at 16Khz. Emotion Recognition (ER) predicts an emotion class for each utterance. The most widely used ER dataset IEMOCAP is adopted, and we follow the conventional evaluation protocol: we drop the unbalanced emotion classes to leave the final four classes with a similar amount of data points and cross-validate on five folds of the standard splits. For the original model's training and evaluation instructions refer to the S3PRL downstream task README.
- Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF↗
tatekuperus
- Mikivis_gpt2-large-imdb3-GGUF↗
tensorblock
- MergeMonster-13B-20231124-GGUF↗
TheBloke
