Llama-3.2-1B-Instruct
by bartowski · built on Llama 3.2 1B · Official #9 of 32 by downloads
Benchmark scores
Official models are not scored on the UGI Leaderboard. We show downloads and likes instead. Estimated speed: ~25–45 tok/s (estimate), a rough range for a Q4_K_M file of this size on a recent flagship chip (Snapdragon 8 Gen 3 or A17 Pro class). It is not a measurement from this model.
About this model
Llama-3.2-1B-Instruct is a 1B-parameter language model by bartowski, derived from meta-llama/Llama-3.2-1B-Instruct using official GGUF conversion. You can download it and run it on your phone for free.
An official 1B release based on Llama 3.2 1B, intended for everyday chat and writing on a phone. The Q4_K_M file is 0.81 GB.
Technically, it uses the llama architecture, supports a context window of 131,072 tokens (a phone will use far less).
Which RAM sizes can run it?
| Device RAM | iOS-safe | Android-safe |
|---|---|---|
| 4 GB RAM | Fits with Q4_K_M (~0.81 GB) | Fits with Q4_K_M (~0.81 GB) |
| 6 GB RAM | Fits with Q4_K_M (~0.81 GB) | Fits with Q4_K_M (~0.81 GB) |
| 8 GB RAM | Fits with Q4_K_M (~0.81 GB) | Fits with Q4_K_M (~0.81 GB) |
| 12 GB RAM | Fits with Q4_K_M (~0.81 GB) | Fits with Q4_K_M (~0.81 GB) |
| 16 GB+ RAM | Fits with Q4_K_M (~0.81 GB) | Fits with Q4_K_M (~0.81 GB) |
iOS-safe minimum: 4 GB. Android-safe minimum: 4 GB. On iOS we treat about 57% of device RAM as usable (in the 55–60% range), because the system keeps a large share and may evict an app that goes higher. On Android we treat about 67% of device RAM as usable (in the 65–70% range), leaving room for the system and the app. See the guide.
Run it on your phone
Compatible apps:
iOS
- PocketPal AI — Free on the App Store. Can search Hugging Face and load a GGUF file on the device.
- Layla — On the App Store as a paid app. Load a custom GGUF from files on the device.
Android
- PocketPal AI — Free on Google Play. Can search Hugging Face and load a GGUF file on the device.
- Layla — On Google Play. Load a custom GGUF from storage. A limited free APK is also offered on the developer site.
- ChatterUI — Free and open source. Install the APK from the GitHub releases page. iOS is not available.
Hugging Face repository ID:
bartowski/Llama-3.2-1B-Instruct-GGUFRecommended file: Q4_K_M — Llama-3.2-1B-Instruct-Q4_K_M.gguf (about 0.81 GB)
- Install one of the apps above for your operating system. PocketPal AI is free on both iOS and Android and can search Hugging Face directly.
- In the app, add a model from Hugging Face and paste this repository ID:
bartowski/Llama-3.2-1B-Instruct-GGUF - Download the Q4_K_M file (
Llama-3.2-1B-Instruct-Q4_K_M.gguf) (about 0.81 GB). Use wifi. This is the only step that needs internet. - Load the file and start chatting. Switch on airplane mode if you like: it keeps working. A first prompt to try:
I'm considering a decision this week. Give me the strongest case for it, the strongest case against it, and the one fact that would change my mind. Keep it short.
If the app is killed or feels slow, close other apps, try the smaller file, or pick a model with a lower iOS-safe or Android-safe minimum. On a computer, the same files work in LM Studio, Ollama and llama.cpp.
Available GGUF files (18)
| Quantization | Size | Download |
|---|---|---|
| IQ3_M Llama-3.2-1B-Instruct-IQ3_M.gguf | 657 MB | Download |
| Q3_K_L Llama-3.2-1B-Instruct-Q3_K_L.gguf | 733 MB | Download |
| IQ4_XS Llama-3.2-1B-Instruct-IQ4_XS.gguf | 743 MB | Download |
| Q4_0 Llama-3.2-1B-Instruct-Q4_0_4_4.gguf | 771 MB | Download |
| Q4_0 Llama-3.2-1B-Instruct-Q4_0_4_8.gguf | 771 MB | Download |
| Q4_0 Llama-3.2-1B-Instruct-Q4_0_8_8.gguf | 771 MB | Download |
| Q4_0 Llama-3.2-1B-Instruct-Q4_0.gguf | 773 MB | Download |
| Q4_K_S Llama-3.2-1B-Instruct-Q4_K_S.gguf | 776 MB | Download |
| Q3_K Llama-3.2-1B-Instruct-Q3_K_XL.gguf | 796 MB | Download |
| Q4_K_MRECOMMENDED Llama-3.2-1B-Instruct-Q4_K_M.gguf | 808 MB | Download |
| Q4_K_L Llama-3.2-1B-Instruct-Q4_K_L.gguf | 871 MB | Download |
| Q5_K_S Llama-3.2-1B-Instruct-Q5_K_S.gguf | 893 MB | Download |
| Q5_K_M Llama-3.2-1B-Instruct-Q5_K_M.gguf | 912 MB | Download |
| Q5_K_L Llama-3.2-1B-Instruct-Q5_K_L.gguf | 975 MB | Download |
| Q6_K Llama-3.2-1B-Instruct-Q6_K.gguf | 1.02 GB | Download |
| Q6_K_L Llama-3.2-1B-Instruct-Q6_K_L.gguf | 1.09 GB | Download |
| Q8_0 Llama-3.2-1B-Instruct-Q8_0.gguf | 1.32 GB | Download |
| F16 Llama-3.2-1B-Instruct-f16.gguf | 2.48 GB | Download |
Direct downloads from bartowski/Llama-3.2-1B-Instruct-GGUF on Hugging Face. Lower Q numbers are smaller and slightly less accurate.