Models that fit 8 GB RAM

66 models fit a device with 8 GB of memory by the size rule of thumb. Pick iOS or Android below for a stricter usable-memory check. 1 of them fit by using their smaller Q3_K_M file. Download once, then use it offline with no account and no API fees.

Can my phone run this?

Operating system

Showing 24 of 44 models (filtered from 135)

Qwen3.5-4B-SOMPOA-heresy-v2

by MuXodious · built on Qwen3.5 4B
#1
Uncensored4BThinkingVision
Uncensored IQ 44.7
Reasoning22.4
Answers10/10
19Kdownloads9likes

Qwen3.5-4B-SOMPOA-heresy-v2 is a 4B model by MuXodious of Qwen3.5 4B, using heretic, an automated abliteration tool. It can read images and writes out its reasoning before it answers. The Q4_K_M file is 2.71 GB.

Run it with PocketPal (iOS, Android), ChatterUI (Android) or Layla (iOS, Android).

iOS-safe from 4 GB · Android-safe from 4 GB · 2.71 GB download · ~12–22 tok/s (estimate)

Qwen3.5-4B-ARA-heresy-v2

by MuXodious · built on Qwen3.5 4B
#3
Uncensored4BThinkingVision
Uncensored IQ 40.5
Reasoning22.6
Answers9/10
1.9Kdownloads1likes

Qwen3.5-4B-ARA-heresy-v2 is a 4B model by MuXodious of Qwen3.5 4B, using heretic, an automated abliteration tool. It can read images and writes out its reasoning before it answers. The Q4_K_M file is 2.71 GB.

Run it with PocketPal (iOS, Android), ChatterUI (Android) or Layla (iOS, Android).

iOS-safe from 4 GB · Android-safe from 4 GB · 2.71 GB download · ~12–22 tok/s (estimate)

Qwen3.5-4B-PaperWitch-heresy-v2

by MuXodious · built on Qwen3.5 4B
#5
Uncensored4BThinkingVision
Uncensored IQ 41.7
Reasoning20.9
Answers9.5/10
754downloads2likes

Qwen3.5-4B-PaperWitch-heresy-v2 is a 4B model by MuXodious of Qwen3.5 4B, using heretic, an automated abliteration tool. It can read images and writes out its reasoning before it answers. The Q4_K_M file is 2.71 GB.

Run it with PocketPal (iOS, Android), ChatterUI (Android) or Layla (iOS, Android).

iOS-safe from 4 GB · Android-safe from 4 GB · 2.71 GB download · ~12–22 tok/s (estimate)

Qwen3.5-4B-MiniFantasy

by Nubinu · built on Qwen3.5 4B SOMPOA heresy v2
#8
Uncensored4BThinking
Uncensored IQ 41
Reasoning17.1
Answers9.2/10
1.6Kdownloads1likes

Qwen3.5-4B-MiniFantasy is a 4B model by Nubinu of Qwen3.5 4B SOMPOA heresy v2, using norm-preserving abliteration (MPOA). It writes out its reasoning before it answers. The Q4_K_M file is 2.71 GB.

Run it with PocketPal (iOS, Android), ChatterUI (Android) or Layla (iOS, Android).

iOS-safe from 6 GB · Android-safe from 6 GB · 2.71 GB download · ~12–22 tok/s (estimate)

Qwen3-4B-Thinking-2507-MPOA

by YanLabs · built on Qwen3 4B Thinking
#11
Uncensored4BThinking
Uncensored IQ 42.2
Reasoning15
Answers8.5/10
300downloads1likes

Qwen3-4B-Thinking-2507-MPOA is a 4B model by YanLabs of Qwen3 4B Thinking, using norm-preserving abliteration (MPOA). It writes out its reasoning before it answers. The Q4_K_M file is 2.5 GB.

Run it with PocketPal (iOS, Android), ChatterUI (Android) or Layla (iOS, Android).

iOS-safe from 4 GB · Android-safe from 4 GB · 2.5 GB download · ~12–22 tok/s (estimate)

Qwen3-4B-Thinking-2507-gabliterated

by Goekdeniz-Guelmez · built on Qwen3 4B Thinking
#12
Uncensored4BThinking
Uncensored IQ 40.1
Reasoning16.7
Answers9.5/10
333downloads0likes

Qwen3-4B-Thinking-2507-gabliterated is a 4B model by Goekdeniz-Guelmez of Qwen3 4B Thinking, using abliteration. It writes out its reasoning before it answers. The Q4_K_M file is 2.5 GB.

Run it with PocketPal (iOS, Android), ChatterUI (Android) or Layla (iOS, Android).

iOS-safe from 4 GB · Android-safe from 4 GB · 2.5 GB download · ~12–22 tok/s (estimate)

Qwen3-4B-Sky-High-Hermes-gabliterated

by Goekdeniz-Guelmez · built on Qwen3 4B Sky High Hermes
#25
Uncensored4BThinking
Uncensored IQ 41.9
Reasoning11.9
Answers9.8/10
305downloads5likes

Qwen3-4B-Sky-High-Hermes-gabliterated is a 4B model by Goekdeniz-Guelmez of Qwen3 4B Sky High Hermes, using abliteration. It writes out its reasoning before it answers. The Q4_K_M file is 2.5 GB.

Run it with PocketPal (iOS, Android), ChatterUI (Android) or Layla (iOS, Android).

iOS-safe from 4 GB · Android-safe from 4 GB · 2.5 GB download · ~12–22 tok/s (estimate)

Qwen3-4B-Instruct-2507-MPOA

by YanLabs · built on Qwen3 4B
#34
Uncensored4B
Uncensored IQ 34.4
Reasoning16.7
Answers7.8/10
175downloads1likes

Qwen3-4B-Instruct-2507-MPOA is a 4B model by YanLabs of Qwen3 4B, using norm-preserving abliteration (MPOA). The Q4_K_M file is 2.5 GB.

Run it with PocketPal (iOS, Android), ChatterUI (Android) or Layla (iOS, Android).

iOS-safe from 4 GB · Android-safe from 4 GB · 2.5 GB download · ~12–22 tok/s (estimate)

Tema_Q-X-4B

by temaq-org · built on Qwen3 4B
#35
Uncensored4BThinking
Uncensored IQ 38.5
Reasoning12.2
Answers8.5/10
79downloads0likes

Tema_Q-X-4B is a 4B model by temaq-org of Qwen3 4B, using community fine-tuning. It writes out its reasoning before it answers. Languages noted on the card include Japanese. The Q4_K_M file is 2.5 GB.

Run it with PocketPal (iOS, Android), ChatterUI (Android) or Layla (iOS, Android).

iOS-safe from 4 GB · Android-safe from 4 GB · 2.5 GB download · ~12–22 tok/s (estimate)

Qwen-SEA-LION-v4-4B-VL-Magic_decensored

by MagicalAlchemist · built on Qwen SEA LION v4 4B VL
#36
Uncensored4B
Uncensored IQ 36.3
Reasoning14.2
Answers8.5/10
265downloads1likes

Qwen-SEA-LION-v4-4B-VL-Magic_decensored is a 4B model by MagicalAlchemist of Qwen SEA LION v4 4B VL, using heretic, an automated abliteration tool. It can look at a photo or screenshot and answer questions about it. Languages noted on the card include Vietnamese, Indonesian, Thai. The Q4_K_M file is 2.5 GB.

Run it with PocketPal (iOS, Android), ChatterUI (Android) or Layla (iOS, Android).

iOS-safe from 4 GB · Android-safe from 4 GB · 2.5 GB download · ~12–22 tok/s (estimate)

Qwen3-4B-Instruct-2507-gabliterated

by Goekdeniz-Guelmez · built on Qwen3 4B
#40
Uncensored4B
Uncensored IQ 35
Reasoning13.9
Answers8.5/10
106downloads3likes

Qwen3-4B-Instruct-2507-gabliterated is a 4B model by Goekdeniz-Guelmez of Qwen3 4B, using abliteration. The Q4_K_M file is 2.5 GB.

Run it with PocketPal (iOS, Android), ChatterUI (Android) or Layla (iOS, Android).

iOS-safe from 4 GB · Android-safe from 4 GB · 2.5 GB download · ~12–22 tok/s (estimate)

Uncensored4B
Uncensored IQ 33
Reasoning15.8
Answers6.8/10
758downloads4likes

Qwen3-4B-Instruct-2507-heretic is a 4B model by p-e-w, using heretic, an automated abliteration tool. The Q4_K_M file is 2.5 GB.

Run it with PocketPal (iOS, Android), ChatterUI (Android) or Layla (iOS, Android).

iOS-safe from 4 GB · Android-safe from 4 GB · 2.5 GB download · ~12–22 tok/s (estimate)

Huihui-Qwen3-4B-Instruct-2507-abliterated

by huihui-ai · built on Qwen3 4B
#48
Uncensored4B
Uncensored IQ 33
Reasoning14
Answers8.5/10
31Kdownloads17likes

Huihui-Qwen3-4B-Instruct-2507-abliterated is a 4B model by huihui-ai of Qwen3 4B, using abliteration. The Q4_K_M file is 2.5 GB.

Run it with PocketPal (iOS, Android), ChatterUI (Android) or Layla (iOS, Android).

iOS-safe from 4 GB · Android-safe from 4 GB · 2.5 GB download · ~12–22 tok/s (estimate)

Josiefied-Qwen3-4B-abliterated-v1

by Goekdeniz-Guelmez · built on Qwen3 4B
#49
Uncensored4BThinking
Uncensored IQ 36.4
Reasoning9.7
Answers8/10
827downloads8likes

Josiefied-Qwen3-4B-abliterated-v1 is a 4B model by Goekdeniz-Guelmez of Qwen3 4B, using abliteration. It writes out its reasoning before it answers. The Q4_K_M file is 2.5 GB.

Run it with PocketPal (iOS, Android), ChatterUI (Android) or Layla (iOS, Android).

iOS-safe from 6 GB · Android-safe from 4 GB · 2.5 GB download · ~12–22 tok/s (estimate)

Uncensored5B · 1.7B activeThinking
Uncensored IQ 34.4
Reasoning9.5
Answers7.8/10
510downloads5likes

Huihui-MoE-5B-A1.7B-abliterated is a 5B · 1.7B active model by huihui-ai, using abliteration. It writes out its reasoning before it answers. The Q4_K_M file is 3.2 GB.

Run it with PocketPal (iOS, Android), ChatterUI (Android) or Layla (iOS, Android).

iOS-safe from 6 GB · Android-safe from 4 GB · 3.2 GB download · ~8–16 tok/s (estimate)

Josiefied-Qwen3-4B-Instruct-2507-gabliterated-v2

by Goekdeniz-Guelmez · built on Qwen3 4B
#55
Uncensored4B
Uncensored IQ 30.4
Reasoning13
Answers7.2/10
239downloads6likes

Josiefied-Qwen3-4B-Instruct-2507-gabliterated-v2 is a 4B model by Goekdeniz-Guelmez of Qwen3 4B, using abliteration. The Q4_K_M file is 2.5 GB.

Run it with PocketPal (iOS, Android), ChatterUI (Android) or Layla (iOS, Android).

iOS-safe from 4 GB · Android-safe from 4 GB · 2.5 GB download · ~12–22 tok/s (estimate)

gemma-3-4b-it-null-space-abliterated

by jwest33 · built on Gemma 3 4B
#56
Uncensored4BVision
Uncensored IQ 31.2
Reasoning11.5
Answers8.2/10
732downloads1likes

gemma-3-4b-it-null-space-abliterated is a 4B model by jwest33 of Gemma 3 4B, using norm-preserving abliteration (MPOA). It can look at a photo or screenshot and answer questions about it. The Q4_K_M file is 2.49 GB.

Run it with PocketPal (iOS, Android), ChatterUI (Android) or Layla (iOS, Android).

iOS-safe from 6 GB · Android-safe from 4 GB · 2.49 GB download · ~12–22 tok/s (estimate)

#58
Uncensored3B
Uncensored IQ 32.7
Reasoning8.7
Answers7/10
324downloads4likes

BlackSheep-Llama3.2-3B is a 3B model by TroyDoesAI, using uncensoring. The Q4_K_M file is 2.02 GB.

Run it with PocketPal (iOS, Android), ChatterUI (Android) or Layla (iOS, Android).

iOS-safe from 4 GB · Android-safe from 4 GB · 2.02 GB download · ~12–22 tok/s (estimate)

Veiled-Calla-4B

by soob3123 · built on Gemma 3 4B
#59
Uncensored4B
Uncensored IQ 33.9
Reasoning7
Answers7.8/10
43downloads2likes

Veiled-Calla-4B is a 4B model by soob3123 of Gemma 3 4B, using uncensoring. The Q4_K_M file is 2.49 GB.

Run it with PocketPal (iOS, Android), ChatterUI (Android) or Layla (iOS, Android).

iOS-safe from 6 GB · Android-safe from 4 GB · 2.49 GB download · ~12–22 tok/s (estimate)

Uncensored2B
Uncensored IQ 29.6
Reasoning11.3
Answers6.5/10
1.8Kdownloads4likes

gemma-2-2b-it-abliterated is a 2B model by IlyaGusev, using abliteration. The Q4_K_M file is 1.71 GB.

Run it with PocketPal (iOS, Android), ChatterUI (Android) or Layla (iOS, Android).

iOS-safe from 4 GB · Android-safe from 4 GB · 1.71 GB download · ~18–30 tok/s (estimate)

Qwen3-1.7B-Magic_decensored

by MagicalAlchemist · built on Qwen3 1.7B Base
#62
Uncensored1.7BThinking
Uncensored IQ 32.3
Reasoning5.5
Answers7.5/10
289downloads0likes

Qwen3-1.7B-Magic_decensored is a 1.7B model by MagicalAlchemist of Qwen3 1.7B Base, using heretic, an automated abliteration tool. It writes out its reasoning before it answers. The Q4_K_M file is 1.11 GB.

Run it with PocketPal (iOS, Android), ChatterUI (Android) or Layla (iOS, Android).

iOS-safe from 4 GB · Android-safe from 4 GB · 1.11 GB download · ~18–30 tok/s (estimate)

Impish_LLAMA_4B_Abliterated

by SicariusSicariiStuff · built on Impish Llama 4B
#63
Uncensored4B
Uncensored IQ 32.3
Reasoning5.5
Answers7.5/10
334downloads0likes

Impish_LLAMA_4B_Abliterated is a 4B model by SicariusSicariiStuff of Impish Llama 4B, using abliteration. The Q4_K_M file is 2.78 GB.

Run it with PocketPal (iOS, Android), ChatterUI (Android) or Layla (iOS, Android).

iOS-safe from 6 GB · Android-safe from 6 GB · 2.78 GB download · ~12–22 tok/s (estimate)

2B-ad

by SicariusSicariiStuff · built on Gemma 2 2B
#65
Uncensored2B
Uncensored IQ 25.1
Reasoning9.7
Answers5.8/10
84downloads1likes

2B-ad is a 2B model by SicariusSicariiStuff of Gemma 2 2B, using a merge of several models (mergekit). The Q4_K_M file is 1.71 GB.

Run it with PocketPal (iOS, Android), ChatterUI (Android) or Layla (iOS, Android).

iOS-safe from 4 GB · Android-safe from 4 GB · 1.71 GB download · ~18–30 tok/s (estimate)

Qwen3.5-4B-Uncensored-HauhauCS-Aggressive

by HauhauCS · built on Qwen3.5 4B
#71
Uncensored4BVision
353Kdownloads880likes

Qwen3.5-4B-Uncensored-HauhauCS-Aggressive is a 4B model by HauhauCS of Qwen3.5 4B, using uncensoring. It can look at a photo or screenshot and answer questions about it. Languages noted on the card include Chinese. The Q4_K_M file is 2.71 GB.

Run it with PocketPal (iOS, Android), ChatterUI (Android) or Layla (iOS, Android).

iOS-safe from 6 GB · Android-safe from 6 GB · 2.71 GB download · ~12–22 tok/s (estimate)

No model matches. Try a higher memory setting, Anything, or clear the search.
Copied