StackMap
Subscribe

airllm vs Ollama

Layer-by-layer inference that runs 70B models on a 4GB GPU — no quantization required; 405B on 8GB, DeepSeek-V3 671B on ~12GB. One AutoModel line for most open model families. — versus — Run Llama, Mistral and other open models locally with a single command and a clean API.

The curated verdict

Both run open models on your own hardware, on opposite sides of one constraint: Ollama gives fast, polished local inference for models that fit your VRAM; AirLLM runs models that don't fit at all — 70B on 4GB — by streaming one layer at a time, at heavy latency cost.

airllmOllama
Stars23k176k
Forks2.6k17k
LanguageJupyter NotebookGo
LicenseApache-2.0MIT
Last activity4 days agotoday
Topicslocallocal
Curated connections216

airllm — the curator's take

The trick is elegant and the tradeoff is brutal, and you should know both: only one layer lives on the GPU at a time, so VRAM scales with layer size instead of model size — that's how 671B fits on a hobbyist card — but every token streams the whole model from disk, so generation runs at seconds-per-token. Use it for batch/offline jobs where 'it fits' beats 'it's fast', for poking at frontier-scale open models on hardware you own, or with block-wise 4/8-bit compression for a ~3x claw-back. NOT a chat or serving solution: Ollama is the fits-in-VRAM daily driver, vLLM the throughput server. Apple-silicon Macs supported via MLX. README carries the author's sponsor/affiliate links — the library stands on its own.

Ollama — the curator's take

Run Llama, Mistral and other open models locally with a single command and a clean API.