GLM-5.2-Int8Mix-NVFP4
This is an experimental hybrid GLM-5.2 checkpoint for vLLM/B12X serving. — the dense, attention, shared-expert, special-head, and MTP...
This is an experimental hybrid GLM-5.2 checkpoint for vLLM/B12X serving. — the dense, attention, shared-expert, special-head, and MTP...
This repo quantizes the model using a data-free quantization tool. This release is prepared for vLLM with compressed-tensors...
INT4 weight-only (W4A16) quantization of Qwen/Qwen3.6-35B-A3B — a hybrid Mixture-of-Experts model (256 experts, top-8, ~3B active) with GatedDeltaNet...
> 2026-05-03 Исправление конфигурации: ropescaling.mscalealldim в config.json был исправлен с 1,0 до 0,0, что соответствует исправлению Mistral выше...
This is a PrismaQuant 4.75-bit mixed-native quantization of mistralai/Mistral-Medium-3.5-128B, exported for vLLM using the compressed-tensors format. This artifact...
MiniMax-M2.7 is our first model deeply participating in its own evolution. M2.7 is capable of building complex agent...
Weights are byte-identical to the upstream quant (config.json and model.safetensors.index.json SHA-256 verified). This mirror exists to provide a...
W4A16 quantization of MiniMaxAI/MiniMax-M2.7, produced with llm-compressor. — Format: compressed-tensors pack-quantized, int4 weights / fp16 activations — Group...
This is a 4-bit AWQ quantization of Google’s Gemma-4-31B-it instruction-tuned multimodal model, optimized for deployment with vLLM. >...
This checkpoint preserves the hybrid Qwen3.5 DeltaNet + softmax architecture and MTP (Multi-Token Prediction) head from the BF16...