01What it can do
- Lightweight: ~4.1 GB VRAM in Q4, fits on a 6–8 GB GPU
- 64k native context
- Fully open OLMo foundation (data + recipe)
- Permissive Apache 2.0 license
- —Unofficial community fine-tune, no Ollama tag
- —Intermediate checkpoint (step 750), quality not stabilized
- —7B: limited capabilities compared with larger models
04Install
Install Ollama for your OS. Check the model and its quantization before downloading. Start with 4096 tokens of context, then check placement with ollama ps. A command below is not proof that a test was run on your machine.
02Required memory
Approximate GPU VRAM required to run this model, including 4k tokens of context overhead. For a longer context, add ~1 GB per 8k-token increment.
What hardware do you need for OLMo 7B CPT Merged (step 750)?
To run OLMo 7B CPT Merged (step 750) locally with Q4 quantization, you need about 4.1 GB of VRAM. An option to compare: RTX 5060 Ti 16GB (ASUS Prime) — leave some headroom for the system and context; check engine compatibility with the GPU.
Affiliate links — commission possible at no extra cost to you; independent recommendation. As an Amazon Associate, BestLLMfor earns from qualifying purchases.
On the go: OLMo 7B CPT Merged (step 750) also runs on a RTX laptop PC (16 GB of VRAM) →
Your private ChatGPT, free, on your own machine in an hour — LM Studio, Ollama, Open WebUI, your documents, no cloud.
- Lifetime online access
- PDF + files
- Lifetime updates
03Expected speed
Tokens generated per second in Q4_K_M, 4k context. Beyond 20 t/s, reading is comfortable. Below 10 t/s, that's just for testing.