Qwen3-0.6B

by unsloth · built on Qwen3 0.6B Base · Official #12 of 32 by downloads

Official0.6BPopularApr 2025
225Kdownloads144likes

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

Qwen3-0.6B is a 0.6B-parameter language model by unsloth, derived from Qwen/Qwen3-0.6B-Base using official GGUF conversion. You can download it and run it on your phone for free.

An official 0.6B release based on Qwen3 0.6B Base, intended for everyday chat and writing on a phone. The Q4_K_M file is 0.4 GB.

Technically, it uses the qwen3 architecture, supports a context window of 40,960 tokens (a phone will use far less).

Which RAM sizes can run it?

Device RAMiOS-safeAndroid-safe
4 GB RAMFits with Q4_K_M (~0.4 GB)Fits with Q4_K_M (~0.4 GB)
6 GB RAMFits with Q4_K_M (~0.4 GB)Fits with Q4_K_M (~0.4 GB)
8 GB RAMFits with Q4_K_M (~0.4 GB)Fits with Q4_K_M (~0.4 GB)
12 GB RAMFits with Q4_K_M (~0.4 GB)Fits with Q4_K_M (~0.4 GB)
16 GB+ RAMFits with Q4_K_M (~0.4 GB)Fits with Q4_K_M (~0.4 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:

unsloth/Qwen3-0.6B-GGUF

Recommended file: Q4_K_M — Qwen3-0.6B-Q4_K_M.gguf (about 0.4 GB)

Download Q4_K_M from Hugging Face

  1. 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.
  2. In the app, add a model from Hugging Face and paste this repository ID:
    unsloth/Qwen3-0.6B-GGUF
  3. Download the Q4_K_M file (Qwen3-0.6B-Q4_K_M.gguf) (about 0.4 GB), or Q3_K_M (about 0.35 GB) if memory is tight. Use wifi. This is the only step that needs internet.
  4. 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 (26)

QuantizationSizeDownload
IQ1_S
Qwen3-0.6B-UD-IQ1_S.gguf
215 MBDownload
IQ1_M
Qwen3-0.6B-UD-IQ1_M.gguf
221 MBDownload
IQ2_XXS
Qwen3-0.6B-UD-IQ2_XXS.gguf
234 MBDownload
IQ2_M
Qwen3-0.6B-UD-IQ2_M.gguf
269 MBDownload
IQ3_XXS
Qwen3-0.6B-UD-IQ3_XXS.gguf
282 MBDownload
Q2_K
Qwen3-0.6B-Q2_K.gguf
296 MBDownload
Q2_K_L
Qwen3-0.6B-Q2_K_L.gguf
296 MBDownload
Q2_K
Qwen3-0.6B-UD-Q2_K_XL.gguf
302 MBDownload
Q3_K_S
Qwen3-0.6B-Q3_K_S.gguf
323 MBDownload
Q3_K_MSMALLER
Qwen3-0.6B-Q3_K_M.gguf
347 MBDownload
Q3_K
Qwen3-0.6B-UD-Q3_K_XL.gguf
357 MBDownload
IQ4_XS
Qwen3-0.6B-IQ4_XS.gguf
368 MBDownload
IQ4_NL
Qwen3-0.6B-IQ4_NL.gguf
382 MBDownload
Q4_0
Qwen3-0.6B-Q4_0.gguf
382 MBDownload
Q4_K_S
Qwen3-0.6B-Q4_K_S.gguf
383 MBDownload
Q4_K_MRECOMMENDED
Qwen3-0.6B-Q4_K_M.gguf
397 MBDownload
Q4_K
Qwen3-0.6B-UD-Q4_K_XL.gguf
405 MBDownload
Q4_1
Qwen3-0.6B-Q4_1.gguf
409 MBDownload
Q5_K_S
Qwen3-0.6B-Q5_K_S.gguf
437 MBDownload
Q5_K_M
Qwen3-0.6B-Q5_K_M.gguf
444 MBDownload
Q5_K
Qwen3-0.6B-UD-Q5_K_XL.gguf
446 MBDownload
Q6_K
Qwen3-0.6B-Q6_K.gguf
495 MBDownload
Q6_K
Qwen3-0.6B-UD-Q6_K_XL.gguf
576 MBDownload
Q8_0
Qwen3-0.6B-Q8_0.gguf
639 MBDownload
Q8_K
Qwen3-0.6B-UD-Q8_K_XL.gguf
844 MBDownload
BF16
Qwen3-0.6B-BF16.gguf
1.20 GBDownload

Direct downloads from unsloth/Qwen3-0.6B-GGUF on Hugging Face. Lower Q numbers are smaller and slightly less accurate.

Similar models

Copied