Search

Run GLM-5.3 (744B), GLM-5.3-Flash (321B), DeepSeek-V4.1-Flash (748B) and MiniMax-M3.1-Flash (428B) on your own GPUs - one engine, one dashboard, OpenAI- and Anthropic-compatible API.

Xolotl: run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 110 GB RAM): ~33 tok/s on agent tasks, ~41 in fast mode, 512K context. Plus GLM-5.3-Flash, Qwen3.8 and LFM3-Omni. MoE experts tiered across VRAM, pinned RAM and NVMe, with Xolotl Direct NVMe->VRAM. OpenAI + Anthropic API.

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, Phi4, ...) (AAAI 2025).

A high-performance framework for training LLMs, VLMs, diffusion, and embodied models on NVIDIA GPUs and Kunlun XPUs. Supports Pi0.5, GR00T-N1.7, FastWAM, Cosmos3, DreamZero, DeepSeek-V4, GLM-5.3, Kimi-K3 and more.

GLM-5: From Vibe Coding to Agentic Engineering

RTX 6000 Pro Wiki — Running Large LLMs (Qwen3.5-397B, Kimi-K2.5, GLM-5) on PCIe GPUs without NVLink

Run DeepSeek-V4.1-Flash / DeepSeek-V4-Flash and GLM-5.3-Flash on SM89 (Ada / RTX 4090) and SM120 (RTX PRO 6000) with vLLM

Run the full 2.78-trillion-parameter Kimi K3 model, DeepSeek V4.1 Flash or GLM-5.3-Flash beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C inference engine.

GLM-5.3-Flash (NVFP4) on 2x NVIDIA DGX Spark - vLLM TP2, 262K context, MTP. World-first deploy recipe: 7 day-0 bugs found and fixed, patched sm121 image, probes and full report.

GLM-5.3 Flash EXL3 for 2-4x DGX Sparks

GLM-5.3-Flash EXL3 on 2x DGX Spark with TensorFold

GLM-5.3-Flash EXL3 on one 24 GB RTX 3090 + DDR4: elastic GPU expert cache, zero-copy experts, AVX2 CPU tier, OpenAI API