Guide
8 min readKimi K3.1 Pro VRAM Requirements
Latest Articles
Guide
9 minMistral Large 4 VRAM Requirements
Mistral Large 4 needs 1.06 TB in FP8, 610 GB in NVFP4 and 233 GB at 1-bit. Which GPU nodes and Macs fit it, and what 128K of KV cache adds.
DevToolLab Team·
Tutorial
8 minHow to Run an LLM Locally on Mac or PC
Install Ollama, run ollama run qwen3.5 and call localhost:11434/v1 from any OpenAI client. What fits in memory, and the 4,096-token default to raise first.
DevToolLab Team·
Guide
9 minQwen3.8 27B VRAM Requirements, Measured
Qwen3.8 27B at Q4_K_M needs 23.74 GB of GPU memory for 128K tokens with a q8_0 cache. llama.cpp's own plan for 16, 24 and 32 GB GPUs.
DevToolLab Team·
More Articles
1–2 of 6
