サイト内検索
AI モデル 84761
- paligemma2-10b-pt-448-jax↗
Google
- psychology-gemma-2-9b-it↗
hienbm
- Qwen-Image-2512-quants↗
Hippotes
- qwen3-1.7b-eagle3-sharegpt-sw768-epoch9-step467800↗
huluhuluu
- HY-WU↗
腾讯
- Qwen3.5-4B-Kazakh↗
issai
- Huihui-Qwen3.8-27B-Coder390-EfficientThink-abliterated-VAL-APEX-I-NanoPlus-V3-GGUF↗
IsValorum
- qwen3.8-flash-coder-44gb-selective-int8↗
Jab1718
**`Qwen3.8-Flash-Coder-44GB-Selective-INT8`** is a high-performance, selective-quantized Mixture-of-Experts (MoE) coding model. Sliced down from the monolithic **`Qwen/Qwen3.8-Flash-Next` (335GB)** and quantized from the **`Qwen3.8-Flash-Coder-85GB-BF16`** parent checkpoint, this model reduces disk and VRAM footprint to exactly **44.29 GB** (a **44.2% VRAM reduction** and **86.8% reduction from base**), enabling full zero-offload deployment on **only 2x 32GB GPUs** (e.g. 2x NVIDIA RTX 5000 Ada, 2x RTX 4090/3090, or 1x A100/H100 80GB). Traditional MoE post-training quantization often quantizes all layers uniformly, which severely degrades the Router Gate and causes **Routing Collapse** (routing tokens to sub-optimal experts). This checkpoint introduces **Selective MoE Quantization**: 1. **Critical High-Precision Modules (Kept in 100% Native BF16):** - **Router Gates:** Retain 100% floating-point routing fidelity across all 48 layers. - **Multi-Head Self-Attention & Linear Attention:** `q_proj`, `k_proj`, `v_proj`, `o_proj`. - **Shared Expert, RMSNorms, Embeddings & LM Head:** Zero quantization loss in embedding projections. 2. **High-Capacity Sparse Experts (Quantized to Symmetric Per-Channel INT8):** - 160 MoE Experts across 48 layers (`gate_up_proj`, `down_proj`). - Symmetrically quantized per-channel with dynamic scaling vectors (`gate_up_proj_scale`, `down_proj_scale`).
- jina-bert-implementation↗
jinaai
- yolov8s-protective-equipment-detection↗
keremberke
