Repository Index

AirLLM 2.8T LLM inference with single 4GB GPU

• chinese-nlp
• finetune
• generative-ai
• instruct-gpt

TranslatedProduction-grade platform for building agentic IM bots - Agent, knowledge base orchestration, plugin system / Bots for Discord / Slack / LINE / Telegram / WeChat(企业微信 (Qiye Weixin, "Enterprise WeChat"), 企微智能机器人 (Qiwei Zhineng Jiqiren, "Enterprise WeChat smart bot"), 公众号 (Gongzhonghao, "official account")) / 飞书 (Feishu, "flying book") / 钉钉 (Dingding, "nail nail") / QQ / Matrix e.g. Integrated with ChatGPT(GPT), DeepSeek, Dify, n8n, Langflow, Coze, Claude, Gemini, GLM, Ollama, SiliconFlow, Kimi, openclaw / hermes agent, deerflow

• qq
• openai
• agent
• llm

A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.

• avx2
• c99
• cpu-inference
• deep-learning

Run 35B MoE models in ~2.5 GB of RAM. Weights stream from SSD; a trained router predicts loads a step ahead. Mac, iPhone, Android, Windows supported

Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.

• kv-cache
• llm-inference
• local-llm
• quantization

Run a 105 GB AI model on a Mac that can't hold it. Qwen3.8-Flash-Next 4-bit, streamed from SSD on 16–64 GB Apple Silicon Macs. Fully native Swift, MLX and Metal. Offline, no Python. CLI, Swift library, and Ollama/OpenAI/Anthropic APIs. Works with Claude Code and Codex.

• apple-silicon
• llm
• llm-inference
• local-llm

37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than your RAM, pure C, CPU or GPU.

• avx2
• c
• cpu-inference
• gguf

Xolotl (formerly Strata-DSV4.1): run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 90 GB RAM) at up to ~27 tok/s, 512K context, October 1017 builds included. Plus GLM-5.3-Flash and Qwen3.8. MoE experts tiered across VRAM, pinned RAM and NVMe; OpenAI + Anthropic API.

• cuda
• deepseek
• deepseek-v4
• gguf

BulkFormer: A large-scale foundation model for human bulk transcriptomes

AI-Driven Full-Text Screening and Data Extraction for Systematic Reviews and Evidence Synthesis

• academic-research
• ai-assistant
• ai-tool
• data-extraction