Models that fit 12 GB RAM

127 models fit a device with 12 GB of memory by the size rule of thumb. Pick iOS or Android below for a stricter usable-memory check. 20 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 48 of 96 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)

Qwen3.5-9B-heretic-v2

by trohrbaugh · built on Qwen3.5 9B Base
#2
Uncensored9BThinkingVision
Uncensored IQ 40.5
Reasoning24.2
Answers9.5/10
9.7Kdownloads3likes

Qwen3.5-9B-heretic-v2 is a 9B model by trohrbaugh of Qwen3.5 9B Base, using heretic, an automated abliteration tool. It can read images and writes out its reasoning before it answers. The Q4_K_M file is 5.63 GB.

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

iOS-safe from 12 GB · Android-safe from 8 GB · 5.63 GB download · ~6–12 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)

Huihui-Qwen3.5-9B-abliterated

by huihui-ai · built on Qwen3.5 9B
#4
Uncensored9BThinkingVision
Uncensored IQ 43.2
Reasoning19.8
Answers9.5/10
478Kdownloads84likes

Huihui-Qwen3.5-9B-abliterated is a 9B model by huihui-ai of Qwen3.5 9B, using abliteration. It can read images and writes out its reasoning before it answers. The Q4_K_M file is 5.63 GB.

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

iOS-safe from 12 GB · Android-safe from 8 GB · 5.63 GB download · ~6–12 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)

Qwen3-8B-heretic

by jbeslt · built on Qwen3 8B Base
#6
Uncensored8BThinking
Uncensored IQ 39.9
Reasoning19.1
Answers8.2/10
11Kdownloads5likes

Qwen3-8B-heretic is a 8B model by jbeslt of Qwen3 8B Base, using heretic, an automated abliteration tool. It writes out its reasoning before it answers. The Q4_K_M file is 5.03 GB.

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

iOS-safe from 8 GB · Android-safe from 8 GB · 5.03 GB download · ~6–12 tok/s (estimate)

Tema_Q-R4.2

by temaq-org
#7
Uncensored9B
Uncensored IQ 43.9
Reasoning14.7
Answers8.2/10
415downloads1likes

Tema_Q-R4.2 is a 9B model by temaq-org, using community fine-tuning. Languages noted on the card include Japanese, Chinese. The Q4_K_M file is 5.76 GB.

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

iOS-safe from 12 GB · Android-safe from 8 GB · 5.76 GB download · ~6–12 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)

Tema_Q-R3.1

by temaq-org
#9
Uncensored9B
Uncensored IQ 41.4
Reasoning16.7
Answers8/10
260downloads1likes

Tema_Q-R3.1 is a 9B model by temaq-org, using community fine-tuning. Languages noted on the card include Japanese, Chinese. The Q4_K_M file is 5.76 GB.

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

iOS-safe from 12 GB · Android-safe from 8 GB · 5.76 GB download · ~6–12 tok/s (estimate)

Qwen-SEA-LION-v4-8B-VL-Magic_decensored

by MagicalAlchemist · built on Qwen SEA LION v4 8B VL
#10
Uncensored8B
Uncensored IQ 41.7
Reasoning15.8
Answers9.2/10
382downloads1likes

Qwen-SEA-LION-v4-8B-VL-Magic_decensored is a 8B model by MagicalAlchemist of Qwen SEA LION v4 8B 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 5.03 GB.

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

iOS-safe from 8 GB · Android-safe from 8 GB · 5.03 GB download · ~6–12 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)

gemma-4-E4B-it-heretic

by coder3101 · built on Gemma 4 E4B
#13
Uncensored8B · 4.5B activeThinkingVision
Uncensored IQ 37.7
Reasoning18.7
Answers9.8/10
3Kdownloads6likes

gemma-4-E4B-it-heretic is a 8B · 4.5B active model by coder3101 of Gemma 4 E4B, using heretic, an automated abliteration tool. It can read images and writes out its reasoning before it answers. The Q4_K_M file is 5.34 GB.

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

iOS-safe from 12 GB · Android-safe from 8 GB · 5.34 GB download · ~6–12 tok/s (estimate)

Tema_Q-X

by temaq-org · built on Gemma 2 9B
#14
Uncensored9B
Uncensored IQ 41.7
Reasoning14.1
Answers8.2/10
309downloads1likes

Tema_Q-X is a 9B model by temaq-org of Gemma 2 9B, using community fine-tuning. Languages noted on the card include Japanese. The Q4_K_M file is 5.76 GB.

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

iOS-safe from 12 GB · Android-safe from 8 GB · 5.76 GB download · ~6–12 tok/s (estimate)

Llama-3.3-8B-Instruct-128K_Abliterated

by SicariusSicariiStuff · built on Llama 3.3 8B 128K
#15
Uncensored8B
Uncensored IQ 39
Reasoning16.6
Answers7.8/10
309downloads1likes

Llama-3.3-8B-Instruct-128K_Abliterated is a 8B model by SicariusSicariiStuff of Llama 3.3 8B 128K, using abliteration. The Q4_K_M file is 4.92 GB.

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

iOS-safe from 12 GB · Android-safe from 8 GB · 4.92 GB download · ~6–12 tok/s (estimate)

Assistant_Pepe_8B

by SicariusSicariiStuff · built on Llama 3.1 Nemotron 8B UltraLong 1M Abliterated
#16
Uncensored8B
Uncensored IQ 38.1
Reasoning17.4
Answers8.8/10
690downloads19likes

Assistant_Pepe_8B is a 8B model by SicariusSicariiStuff of Llama 3.1 Nemotron 8B UltraLong 1M Abliterated, using abliteration. The Q4_K_M file is 4.93 GB.

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

iOS-safe from 12 GB · Android-safe from 8 GB · 4.93 GB download · ~6–12 tok/s (estimate)

Josiefied-Qwen3-8B-abliterated-v1

by Goekdeniz-Guelmez · built on Qwen3 8B
#17
Uncensored8BThinking
Uncensored IQ 41
Reasoning14.2
Answers8.2/10
3.1Kdownloads32likes

Josiefied-Qwen3-8B-abliterated-v1 is a 8B model by Goekdeniz-Guelmez of Qwen3 8B, using abliteration. It writes out its reasoning before it answers. The Q4_K_M file is 5.03 GB.

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

iOS-safe from 8 GB · Android-safe from 8 GB · 5.03 GB download · ~6–12 tok/s (estimate)

Llama-3.1-8B-Instruct-heretic

by p-e-w · built on Llama 3.1 8B
#19
Uncensored8B
Uncensored IQ 38.5
Reasoning16.7
Answers7.8/10
489downloads1likes

Llama-3.1-8B-Instruct-heretic is a 8B model by p-e-w of Llama 3.1 8B, using heretic, an automated abliteration tool. Languages noted on the card include German. The Q4_K_M file is 4.92 GB.

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

iOS-safe from 8 GB · Android-safe from 6 GB · 4.92 GB download · ~6–12 tok/s (estimate)

gemma-4-E4B-it-ultra-uncensored-heretic

by llmfan46 · built on Gemma 4 E4B
#21
Uncensored8B · 4.5B activeThinkingVision
Uncensored IQ 38.5
Reasoning16.4
Answers10/10
146Kdownloads329likes

gemma-4-E4B-it-ultra-uncensored-heretic is a 8B · 4.5B active model by llmfan46 of Gemma 4 E4B, using heretic, an automated abliteration tool. It can read images and writes out its reasoning before it answers. The Q4_K_M file is 5.34 GB.

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

iOS-safe from 12 GB · Android-safe from 8 GB · 5.34 GB download · ~6–12 tok/s (estimate)

Uncensored8B
Uncensored IQ 37.5
Reasoning16.7
Answers7.2/10
202downloads2likes

Llama-3.3-8B-Instruct-128K-heretic is a 8B model by aeon37, using heretic, an automated abliteration tool. The Q4_K_M file is 4.92 GB.

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

iOS-safe from 8 GB · Android-safe from 6 GB · 4.92 GB download · ~6–12 tok/s (estimate)

Gemma2-Snowflakes-9B

by yamatazen · built on EZO Humanities 9B Gemma 2
#23
Uncensored9B
Uncensored IQ 40.9
Reasoning13.4
Answers7.5/10
87downloads2likes

Gemma2-Snowflakes-9B is a 9B model by yamatazen of EZO Humanities 9B Gemma 2, using abliteration. Languages noted on the card include Japanese. The Q4_K_M file is 5.76 GB.

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

iOS-safe from 12 GB · Android-safe from 8 GB · 5.76 GB download · ~6–12 tok/s (estimate)

MT2-Gen11-gemma-2-9B

by zelk12 · built on MT Merge6 Gemma 2 9B
#24
Uncensored9B
Uncensored IQ 37.9
Reasoning16
Answers7.8/10
157downloads3likes

MT2-Gen11-gemma-2-9B is a 9B model by zelk12 of MT Merge6 Gemma 2 9B, using abliteration. The Q4_K_M file is 5.76 GB.

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

iOS-safe from 12 GB · Android-safe from 8 GB · 5.76 GB download · ~6–12 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)

Qwen3.5-9B-Claude-4.6-HighIQ-THINKING-HERETIC-UNCENSORED

by DavidAU · built on Qwen3.5 9B heretic v2
#26
Uncensored9BThinkingVision
Uncensored IQ 30.3
Reasoning22.9
Answers6.5/10
9.2Kdownloads25likes

Qwen3.5-9B-Claude-4.6-HighIQ-THINKING-HERETIC-UNCENSORED is a 9B model by DavidAU of Qwen3.5 9B heretic v2, using heretic, an automated abliteration tool. It can read images and writes out its reasoning before it answers. The Q4_K_M file is 5.63 GB.

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

iOS-safe from 12 GB · Android-safe from 8 GB · 5.63 GB download · ~6–12 tok/s (estimate)

Gemma2-Evelyn-9B

by yamatazen · built on Gemma2 BlueMoon 9B
#27
Uncensored9B
Uncensored IQ 37.4
Reasoning15.8
Answers6.5/10
204downloads1likes

Gemma2-Evelyn-9B is a 9B model by yamatazen of Gemma2 BlueMoon 9B, using a Model Stock merge of several models (mergekit). Languages noted on the card include Japanese. The Q4_K_M file is 5.76 GB.

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

iOS-safe from 12 GB · Android-safe from 8 GB · 5.76 GB download · ~6–12 tok/s (estimate)

MT-Gen10-gemma-2-9B

by zelk12 · built on Gemma 9B
#28
Uncensored9B
Uncensored IQ 38.9
Reasoning14
Answers8/10
7downloads1likes

MT-Gen10-gemma-2-9B is a 9B model by zelk12 of Gemma 9B, using abliteration. The Q4_K_M file is 5.76 GB.

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

iOS-safe from 12 GB · Android-safe from 8 GB · 5.76 GB download · ~6–12 tok/s (estimate)

Llama-3.1-8B-Instruct-Uncensored

by ccharnkij · built on Llama 3.1 8B
#29
Uncensored8B
Uncensored IQ 35.8
Reasoning17.1
Answers7.5/10
243downloads0likes

Llama-3.1-8B-Instruct-Uncensored is a 8B model by ccharnkij of Llama 3.1 8B, using abliteration. The Q4_K_M file is 4.92 GB.

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

iOS-safe from 8 GB · Android-safe from 6 GB · 4.92 GB download · ~6–12 tok/s (estimate)

NeuralDaredevil-8B-abliterated

by mlabonne · built on Daredevil 8B abliterated
#30
Uncensored8B
Uncensored IQ 33.2
Reasoning19.3
Answers6.5/10
415downloads2likes

NeuralDaredevil-8B-abliterated is a 8B model by mlabonne of Daredevil 8B abliterated, using abliteration. The Q4_K_M file is 4.92 GB.

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

iOS-safe from 8 GB · Android-safe from 6 GB · 4.92 GB download · ~6–12 tok/s (estimate)

Aspire-8B-model_stock

by DreadPoor · built on Llama 3.1 8B Lexi Uncensored V2
#31
Uncensored8B
Uncensored IQ 35.9
Reasoning15.6
Answers6.8/10
405downloads2likes

Aspire-8B-model_stock is a 8B model by DreadPoor of Llama 3.1 8B Lexi Uncensored V2, using abliteration. The Q4_K_M file is 4.92 GB.

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

iOS-safe from 8 GB · Android-safe from 6 GB · 4.92 GB download · ~6–12 tok/s (estimate)

qwen3-vl-8b-instruct-null-space-abliterated

by jwest33 · built on Qwen3 VL 8B
#32
Uncensored8BVision
Uncensored IQ 37.1
Reasoning14.5
Answers8.5/10
769downloads10likes

qwen3-vl-8b-instruct-null-space-abliterated is a 8B model by jwest33 of Qwen3 VL 8B, using community fine-tuning. It can look at a photo or screenshot and answer questions about it. The Q4_K_M file is 5.03 GB.

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

iOS-safe from 12 GB · Android-safe from 8 GB · 5.03 GB download · ~6–12 tok/s (estimate)

Gemma2-Alicia-9B

by yamatazen · built on EZO Common 9B Gemma 2
#33
Uncensored9B
Uncensored IQ 36.2
Reasoning15.1
Answers7/10
70downloads1likes

Gemma2-Alicia-9B is a 9B model by yamatazen of EZO Common 9B Gemma 2, using abliteration. Languages noted on the card include Japanese. The Q4_K_M file is 5.76 GB.

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

iOS-safe from 12 GB · Android-safe from 8 GB · 5.76 GB download · ~6–12 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)

MT2-Gen10-gemma-2-9B

by zelk12 · built on MT1 Gen7 Gemma 2 9B
#37
Uncensored9B
Uncensored IQ 35.1
Reasoning14.7
Answers6.8/10
9downloads1likes

MT2-Gen10-gemma-2-9B is a 9B model by zelk12 of MT1 Gen7 Gemma 2 9B, using abliteration. The Q4_K_M file is 5.76 GB.

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

iOS-safe from 12 GB · Android-safe from 8 GB · 5.76 GB download · ~6–12 tok/s (estimate)

gpt-4o-distil-Llama-3.1-8B-Instruct-PaperWitch-heresy

by MuXodious · built on gpt 4o distil Llama 3.1 8B
#38
Uncensored8B
Uncensored IQ 32.9
Reasoning16.9
Answers7.5/10
1.7Kdownloads14likes

gpt-4o-distil-Llama-3.1-8B-Instruct-PaperWitch-heresy is a 8B model by MuXodious of gpt 4o distil Llama 3.1 8B, using heretic, an automated abliteration tool. The Q4_K_M file is 4.92 GB.

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

iOS-safe from 8 GB · Android-safe from 6 GB · 4.92 GB download · ~6–12 tok/s (estimate)

LatentSoup-modelstock-8b

by Entropicengine · built on LatentDream exp delta 8B
#39
Uncensored8B
Uncensored IQ 33.6
Reasoning16
Answers7.5/10
107downloads1likes

LatentSoup-modelstock-8b is a 8B model by Entropicengine of LatentDream exp delta 8B, using a Model Stock merge of several models (mergekit). The Q4_K_M file is 4.92 GB.

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

iOS-safe from 8 GB · Android-safe from 6 GB · 4.92 GB download · ~6–12 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)

Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct_Abliterated

by SicariusSicariiStuff · built on Llama 3.1 Nemotron 8B UltraLong 1M
#42
Uncensored8B
Uncensored IQ 33
Reasoning15.1
Answers7.2/10
184downloads1likes

Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct_Abliterated is a 8B model by SicariusSicariiStuff of Llama 3.1 Nemotron 8B UltraLong 1M, using abliteration. The Q4_K_M file is 4.93 GB.

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

iOS-safe from 8 GB · Android-safe from 6 GB · 4.93 GB download · ~6–12 tok/s (estimate)

Dusk_Rainbow

by SicariusSicariiStuff
#43
Uncensored8B
Uncensored IQ 35
Reasoning13
Answers7.2/10
424downloads1likes

Dusk_Rainbow is a 8B model by SicariusSicariiStuff, using fine-tuning. The Q4_K_M file is 4.92 GB.

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

iOS-safe from 8 GB · Android-safe from 6 GB · 4.92 GB download · ~6–12 tok/s (estimate)

BaeZel-8B-LINEAR

by DreadPoor · built on Heart Stolen 8B Model Stock
#44
Uncensored8B
Uncensored IQ 31.3
Reasoning16.4
Answers6.2/10
89downloads0likes

BaeZel-8B-LINEAR is a 8B model by DreadPoor of Heart Stolen 8B Model Stock, using a linear merge of several models (mergekit). The Q4_K_M file is 4.92 GB.

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

iOS-safe from 8 GB · Android-safe from 6 GB · 4.92 GB download · ~6–12 tok/s (estimate)

GrayLine-Qwen3-8B

by soob3123 · built on Qwen3 8B
#45
Uncensored8BThinking
Uncensored IQ 34.3
Reasoning13.4
Answers6.2/10
112downloads1likes

GrayLine-Qwen3-8B is a 8B model by soob3123 of Qwen3 8B, using uncensoring. It writes out its reasoning before it answers. The Q4_K_M file is 5.03 GB.

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

iOS-safe from 12 GB · Android-safe from 8 GB · 5.03 GB download · ~6–12 tok/s (estimate)

Dobby-Mini-Unhinged-Llama-3.1-8B

by SentientAGI · built on Llama 3.1 8B
#46
Uncensored8B
Uncensored IQ 32.1
Reasoning15.2
Answers7.5/10
102downloads7likes

Dobby-Mini-Unhinged-Llama-3.1-8B is a 8B model by SentientAGI of Llama 3.1 8B, using fine-tuning. The Q4_K_M file is 4.92 GB.

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

iOS-safe from 12 GB · Android-safe from 8 GB · 4.92 GB download · ~6–12 tok/s (estimate)

Llama-SEA-LION-v3-8B-IT-Magic_decensored

by MagicalAlchemist · built on Llama SEA LION v3 8B
#47
Uncensored8B
Uncensored IQ 33.3
Reasoning13.9
Answers7.2/10
222downloads1likes

Llama-SEA-LION-v3-8B-IT-Magic_decensored is a 8B model by MagicalAlchemist of Llama SEA LION v3 8B, using heretic, an automated abliteration tool. Languages noted on the card include Chinese, Vietnamese, Indonesian. The Q4_K_M file is 4.92 GB.

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

iOS-safe from 8 GB · Android-safe from 6 GB · 4.92 GB download · ~6–12 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)

#50
Uncensored8B
Uncensored IQ 32.5
Reasoning12
Answers7/10
297downloads4likes

BlackSheep-X-Dolphin is a 8B model by TroyDoesAI, using community fine-tuning. The Q4_K_M file is 4.92 GB.

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

iOS-safe from 8 GB · Android-safe from 6 GB · 4.92 GB download · ~6–12 tok/s (estimate)

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