全站搜索
AI 模型 84760
- Qwen3.8-27B-GGUF↗
manubc33
- Ferret_7B-Mistral-7B-Instruct-v0.2-slerp-GGUF↗
MaziyarPanahi
- medicine-chat-GGUF↗
MaziyarPanahi
- Muse-Glimmer-30B-assistant↗
meta-models
**Authors:** Meta Superintelligence Lab **Model Release Date:** August 2026 **License:** Apache 2.0 > [!NOTE] This model card is for the lightweight "drafter" model for Muse Glimmer 30B, based on DFlash. The DFlash block-diffusion model predicts entire blocks of 16 tokens in a single forward pass. The main model then verifies these proposals in parallel, accepting correct tokens and correcting wrong ones. This technique lets Muse Glimmer generate text significantly faster than standard token-by-token generation while producing identical output quality. Muse Glimmer is a 30-billion-parameter causal language model with a dedicated perception encoder, distilled from Muse Spark and purpose-built for autonomous agentic tasks on consumer hardware. The model integrates multi-step reasoning, reliable tool use, multimodal understanding, and failure recovery into a single model that runs locally without requiring cloud infrastructure or network access.
- gemma-4-26B-A4B-it-qat-OptiQ-4bit↗
mlx-community
> **Built with mlx-optiq**, the MLX-native toolkit to quantize, fine-tune, and serve LLMs locally on Apple Silicon, no PyTorch and no cloud. Try the Lab · All OptiQ quants · Docs A 4-bit mixed-precision MLX quant produced by mlx-optiq, built on Google's quantization-aware-trained (QAT) Gemma-4 base. This is the **sparse-MoE** member of the family: 26B total parameters with 128 routed experts (about 4B active per token). OptiQ's sensitivity-guided per-layer bit allocation is applied on top of weights already trained to survive low-bit quantization, and it still beats a uniform 4-bit quant of the same QAT base on the Capability Score. This is a quant of google/gemma-4-26B-A4B-it-qat-q4_0-unquantized. Per-layer bit-widths come from a KL-divergence sensitivity pass on a six-domain calibration mix (prose, reasoning, code, agent, tool-call, constraint-bearing instructions). On this MoE the sensitivity pass identifies the routed experts as where precision matters most, so the allocation puts 8-bit on the experts that need it (42 of 90 expert tensors) plus the sensitive attention and router layers, and keeps the robust ones at 4-bit.
- gpt-oss-120b-MXFP4-Q8↗
mlx-community
This model mlx-community/gpt-oss-120b-MXFP4-Q8 was converted to MLX format from openai/gpt-oss-120b using mlx-lm version **0.27.0**.
- SmolVLM2-2.2B-Instruct-mlx↗
mlx-community
- Assistant_Pepe_32B-GGUF↗
mradermacher
- atlas-v21-gemma4-31b-GGUF↗
mradermacher
- Carnice-Qwen3.6-MoE-35B-A3B-GGUF↗
mradermacher