Which Local LLM Fits Each RAM Tier (2026): File Sizes and Ollama Tags
Pick a model by its file size, not by its parameter count. The table below gives the file size of each pick at each RAM tier, from 16GB to 256GB, and an Ollama tag that resolves. Every size comes from the Hugging Face file tree or the Ollama registry, read on 2026-11-21.
The rule: the file must be smaller than your RAM
A model loads its whole file into memory. Your OS, your apps and the context window (KV cache) need memory too. So pick a file that is clearly smaller than your RAM. A file that is about the same size as your RAM does not fit.
Parameter count does not tell you the file size. gpt-oss 20B is a 12-14 GB file because it ships in MXFP4. A dense 27B model at Q8 is 29 GB. Read the file size.
Fit table: one or more picks per RAM tier
Sizes are GB of 10^9 bytes. “Registry” means the Ollama registry manifest. “HF” means the Hugging Face file tree. All read on 2026-11-21.
| RAM tier | Model and quant | File size | Ollama tag | Source |
|---|---|---|---|---|
| 16GB | Qwen 3.5 9B Q8_0 | 9.53 GB | qwen3.5:9b-q8_0 | Registry |
| 16GB (tight) | gpt-oss 20B MXFP4 | 13.79 GB | gpt-oss:20b | Registry |
| 24GB | Qwen 3.6 27B Q4_K_M | 16.84 GB | qwen3.6:27b | Registry |
| 24GB | Qwen 3.6 35B-A3B Q4_K_M | 21.72 GB | qwen3.6:35b | Registry |
| 32GB | Qwen3.8 27B UD-Q6_K | 21.98 GB | hf.co/unsloth/Qwen3.8-27B-GGUF:UD-Q6_K | HF |
| 32GB | Gemma 4 26B-A4B | 17.07 GB | gemma4:26b-a4b | Registry |
| 32GB | gpt-oss 20B Q8_0 | 12.11 GB | hf.co/unsloth/gpt-oss-20b-GGUF:Q8_0 | HF |
| 32GB | Nemotron Cascade 2 30B | 24.27 GB | nemotron-cascade-2:30b | Registry |
| 48GB | Qwen 3.6 27B Q8_0 | 29.05 GB | qwen3.6:27b-q8_0 | Registry |
| 48GB | Qwen 3.6 35B-A3B UD-Q6_K | 29.31 GB | hf.co/unsloth/Qwen3.6-35B-A3B-GGUF:UD-Q6_K | HF |
| 64GB | Qwen3.8 27B Q8_0 | 29.05 GB | hf.co/unsloth/Qwen3.8-27B-GGUF:Q8_0 | HF |
| 64GB | Qwen 3.6 35B-A3B Q8_0 | 36.90 GB | hf.co/unsloth/Qwen3.6-35B-A3B-GGUF:Q8_0 | HF |
| 96GB | gpt-oss 120B MXFP4 | 65.37 GB | gpt-oss:120b | Registry |
| 96GB | Qwen 3.5 122B-A10B Q4_K_M | 81.37 GB | qwen3.5:122b | Registry |
| 128GB | gpt-oss 120B MXFP4 | 65.37 GB | gpt-oss:120b | Registry |
| 128GB | Llama 4 Scout Q4_K_M | 67.44 GB | llama4:scout | Registry |
| 128GB | Qwen 3.5 122B-A10B Q4_K_M | 81.37 GB | qwen3.5:122b-a10b-q4_K_M | Registry |
| 192GB | DeepSeek V4 Flash UD-IQ4_XS | 136.66 GB | none checked | HF (unsloth/DeepSeek-V4-Flash-0731-GGUF) |
| 256GB | Llama 4 Maverick UD-Q3_K_XL | 179.55 GB | none checked | HF (unsloth/Llama-4-Maverick-17B-128E-Instruct-GGUF) |
| 256GB | Llama 4 Maverick IQ4_XS | 214.32 GB | none checked | HF (same repo) |
qwen3.5:122b and qwen3.5:122b-a10b-q4_K_M resolve to the same 81.37 GB file. The 192GB and 256GB files are split GGUFs. We list no pull tag for them because we did not check one.
Models that do not fit the tier people expect
| Model | File size | Common claim | Fact |
|---|---|---|---|
| gpt-oss 120B | 65.37 GB | ”Fits 64GB” | The file alone is larger than 64GB. Use 96GB or more. |
| Llama 4 Scout Q4_K_M | 65.36-67.44 GB | ”Fits 64GB” | Too large for 64GB. The IQ4_XS file is 57.65 GB, with little room for context. |
| Llama 4 Maverick Q4_K_M | 242.77 GB | ”Fits 128GB at Q4” | The file is far larger than 128GB. Even UD-Q3_K_XL is 179.55 GB. |
| DeepSeek V4 Flash | 128.21 GB at UD-Q3_K_XL, 136.66 GB at UD-IQ4_XS | ”Fits 128GB at Q4” | The Q4 file is larger than 128GB. |
What this page does not measure
This page gives no speed, quality or tool-call success numbers. Speed depends on memory bandwidth, quant and context length. For those, read the tier guide for your RAM. Each guide cites its own sources.
- 16GB picks
- 24GB picks
- 32GB picks
- 48GB picks
- 64GB picks
- 96GB picks
- 128GB picks
- M2 Ultra-specific guide
- Local LLM Fit and Speed Estimator
How to check a file size yourself
For an Ollama library tag, open https://ollama.com/library/<model>/tags. Each tag shows its size. For an hf.co tag, open the repo’s “Files” tab on Hugging Face and read the size of the .gguf file. Split files list each part, so add the parts.
A laptop for the 32GB tier picks
36GB of unified memory holds every 32GB-tier file in the table above.
Amazon affiliate links — we earn a small commission at no cost to you.