Ollama concurrency: NUM_PARALLEL and MAX_QUEUE
The second request waits, or it is refused: what OLLAMA_NUM_PARALLEL and OLLAMA_MAX_QUEUE really control, and why every parallel slot costs you memory.
#vram
Filtering by topic #vram · clear
What it takes to self-host Kimi K3
Kimi K3 is 2.8 trillion parameters. Here is the VRAM arithmetic, the KV cache math, and the three honest ways to run it without a 32 GPU cluster.
Self-hosted AI video generator: the reality
What open video models really produce in July 2026, the VRAM class each one needs, what a five second clip costs on a rented GPU, and when to use an API.
Ollama quantization: Q4 vs Q8 vs fp16
Pick an Ollama quantization with arithmetic instead of guesswork: what q4_K_M, q8_0 and fp16 cost in RAM, and where the quality actually drops.
What does an AI server cost to build?
The accelerator sets most of the bill. Learn how VRAM, memory bandwidth, power headroom, cooling and your own tariff decide what the rest costs.