Process killed (OOM killer) when loading large model

Q: How do you fix "Process killed (OOM killer) when loading large model"?

**Confirm OOM was the cause:** ```bash sudo dmesg | tail -50 # Look for "Out of memory: Killed process X" ``` **Add swap** (provides "soft" memory at disk speed): ```bash sudo fallocate -l 32G /swapfile sudo chmod 600 /swapfile sudo mkswap /swapfile sudo swapon /swapfile echo '/swapfile swap swap defaults 0 0' | sudo tee -a /etc/fstab ``` Loading takes 5-10 minutes the first time but works. **Use a smaller quantization** so the model fits in RAM: ```bash # 70B Q4 ≈ 40 GB. 70B Q2 ≈ 26 GB. Quality drop is severe at Q2 — use only as fallback. ollama pull llama3.3:70b-instruct-q3_K_M # 31 GB, better quality than Q2 ``` **Add physical RAM.** For 70B-class models the practical floor is 64 GB system RAM. 128 GB is comfortable. Apple Silicon's unified memory bypasses this entirely — 128 GB unified runs 70B without swap tricks.

Killed

By Fredoline Eruo · Last verified Jun 12, 2026

Cause

On Linux, the kernel's OOM (Out-Of-Memory) killer terminates processes that try to allocate more memory than available. The terse "Killed" output (no Python traceback) is the giveaway — Python itself never got to handle the error.

Common scenario: pulling a 70B model on a 32 GB RAM machine. The model file (~40 GB at Q4) tries to fit in RAM during load.

Solution

Confirm OOM was the cause:

sudo dmesg | tail -50
# Look for "Out of memory: Killed process X"

Add swap (provides "soft" memory at disk speed):

sudo fallocate -l 32G /swapfile
sudo chmod 600 /swapfile
sudo mkswap /swapfile
sudo swapon /swapfile
echo '/swapfile swap swap defaults 0 0' | sudo tee -a /etc/fstab

Loading takes 5-10 minutes the first time but works.

Use a smaller quantization so the model fits in RAM:

# 70B Q4 ≈ 40 GB. 70B Q2 ≈ 26 GB. Quality drop is severe at Q2 — use only as fallback.
ollama pull llama3.3:70b-instruct-q3_K_M  # 31 GB, better quality than Q2

Add physical RAM. For 70B-class models the practical floor is 64 GB system RAM. 128 GB is comfortable. Apple Silicon's unified memory bypasses this entirely — 128 GB unified runs 70B without swap tricks.

Related errors

Did this fix it?

If your case was different, email Contact support with what you saw and we'll update the page. If it worked but took different commands on your platform, we want to know that too.