全站搜索
AI 模型 85012
- Qwen3-4B-quantized.w4a16↗
RedHatAI
This model was obtained by quantizing the weights of Qwen3-4B to INT4 data type. This optimization reduces the number of bits per parameter from 16 to 4, reducing the disk size and GPU memory requirements by approximately 75%. Only the weights of the linear operators within transformers blocks are quantized. Weights are quantized using a asymmetric per-group scheme, with group size 64. The GPTQ algorithm is applied for quantization, as implemented in the llm-compressor library. The model was evaluated on the OpenLLM leaderboard tasks (versions 1 and 2), using lm-evaluation-harness, and on reasoning tasks using lighteval. vLLM was used for all evaluations.
- Qwen3.5-4B-Clarity-1.0-GGUF↗
Regic1d3
- anthracite-org_-_magnum-v2-32b-gguf↗
RichardErkhov
- semcoder_-_semcoder_1030-gguf↗
RichardErkhov
- tlphams_-_solar-10.7b-merged-v0.1-gguf↗
RichardErkhov
- CodeSearch-ModernBERT-Crow-Plus↗
Shuu12121
- DarijaBERT↗
SI2M-Lab
- Assistant_Pepe_32B↗
SicariusSicariiStuff
- deberta-v3-large-tasksource-nli↗
sileod
- A.X-K1↗
skt
**A.X K1** is a large-scale Mixture-of-Experts (MoE) language model designed for efficient high-capacity reasoning and instruction following, and was trained from scratch without initializing from an existing pretrained model. The model contains **519 billion total parameters**, with **33 billion active parameters**, enabling strong performance while maintaining practical inference efficiency. This hybrid design allows the user to choose between in-depth reasoning and response latency depending on task requirements. A.X K1 follows a sparse Mixture-of-Experts architecture in which only a subset of experts is activated per token. This design substantially increases model capacity while keeping the computational cost comparable to dense models with much smaller parameter counts.
