Local LLM model fit
gpt-oss 120B is a 120B gpt-oss model. This page estimates Q4 VRAM fit, Ollama command, context planning, and fallback choices for common local AI GPUs.
Large local reasoning servers, heavy agent orchestration, and high-end homelab inference. Weakness: Not realistic for consumer single-GPU setups below 80GB-class memory.
| Hardware | Examples | Clean capacity | Q4 need | Status | Calculator |
|---|---|---|---|---|---|
| 6 GB VRAM entry GPU | GTX 1660, RTX 2060 6GB | 4.50 GB clean VRAM | 65 GB | Too large | Open calculator |
| 8 GB VRAM mainstream GPU | RTX 3060 Ti, RTX 4060, RTX 3070 | 6.50 GB clean VRAM | 65 GB | Too large | Open calculator |
| 10 GB VRAM older high-end GPU | RTX 3080 10GB | 8.50 GB clean VRAM | 65 GB | Too large | Open calculator |
| 12 GB VRAM local agent GPU | RTX 3060 12GB, RTX 4070 | 10.5 GB clean VRAM | 65 GB | Too large | Open calculator |
| 16 GB VRAM creator GPU | RTX 4060 Ti 16GB, RTX 4080 | 14.5 GB clean VRAM | 65 GB | RAM offload | Open calculator |
| 24 GB VRAM homelab workstation | RTX 3090, RTX 4090 | 22.5 GB clean VRAM | 65 GB | RAM offload | Open calculator |
| 48 GB VRAM workstation | RTX A6000, L40S 48GB | 46.5 GB clean VRAM | 65 GB | RAM offload | Open calculator |
| Apple Silicon 32 GB unified memory | M2 Max 32GB, M3 Max 36GB | 26 GB unified | 65 GB | Too large | Open calculator |
| Quantization | Estimated memory | Use case |
|---|---|---|
| Q4 / 4-bit | 65 GB | Default local inference balance |
| Q5 / 5-bit | 81.3 GB | Better quality, more VRAM |
| Q8 / 8-bit | 130 GB | High quality, much more VRAM |
| FP16 / 16-bit | 260 GB | Mostly workstation/server use |
70B · High-quality local chat and reasoning on workstation-class hardware
46.7B · MoE local reasoning/chat when enough VRAM is available
32B · Strong local coding and architecture work on 24GB GPUs
32B · Heavy local reasoning on 24GB GPUs