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 48 of 66 models (filtered from 135)

Qwen3.5-4B

by unsloth · built on Qwen3.5 4B Base
#3
Official4BVision
1.6Mdownloads578likes

An official 4B vision model based on Qwen3.5 4B Base, made to understand images as well as text. The Q4_K_M file is 2.74 GB.

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

iOS-safe from 6 GB · Android-safe from 4 GB · 2.74 GB download · ~12–22 tok/s (estimate)

Qwen3-4B-Instruct-2507

by unsloth · built on Qwen3 4B 2507
#4
Official4B
896Kdownloads228likes

An official 4B release based on Qwen3 4B 2507, intended for everyday chat and writing on a phone. 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-E2B-it

by unsloth · built on gemma 4 E2B
#6
Official2BVision
814Kdownloads361likes

An official 2B vision model based on gemma 4 E2B, made to understand images as well as text. The Q4_K_M file is 3.11 GB.

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

iOS-safe from 6 GB · Android-safe from 4 GB · 3.11 GB download · ~18–30 tok/s (estimate)

Spark-X2.5-4B-Heretic-jp

by soyaakinohara · built on Spark X2.5 4B Base
#90
NewUncensored4B
590Kdownloads22likes

Spark-X2.5-4B-Heretic-jp is a 4B model by soyaakinohara of Spark X2.5 4B Base, using heretic, an automated abliteration tool. The Q4_K_M file is 2.6 GB.

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

iOS-safe from 6 GB · Android-safe from 4 GB · 2.6 GB download · ~12–22 tok/s (estimate)

gemma-3-1b-it

by ggml-org · built on gemma 3 1b pt
#8
Official1B
542Kdownloads62likes

An official 1B release based on gemma 3 1b pt, intended for everyday chat and writing on a phone. The Q4_K_M file is 0.81 GB.

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

iOS-safe from 4 GB · Android-safe from 4 GB · 0.81 GB download · ~25–45 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)

Llama-3.2-1B-Instruct

by bartowski · built on Llama 3.2 1B
#9
Official1B
276Kdownloads190likes

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.

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

iOS-safe from 4 GB · Android-safe from 4 GB · 0.81 GB download · ~25–45 tok/s (estimate)

Qwen3-VL-4B-Instruct

by unsloth · built on Qwen3 VL 4B
#10
Official4BVision
274Kdownloads80likes

An official 4B vision model based on Qwen3 VL 4B, made to understand images as well as text. 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)

Qwen3-1.7B

by unsloth · built on Qwen3 1.7B Base
#11
Official1.7B
254Kdownloads84likes

An official 1.7B release based on Qwen3 1.7B Base, intended for everyday chat and writing on a phone. 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)

Qwen3-0.6B

by unsloth · built on Qwen3 0.6B Base
#12
Official0.6B
225Kdownloads144likes

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.

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

iOS-safe from 4 GB · Android-safe from 4 GB · 0.4 GB download · ~25–45 tok/s (estimate)

LFM2.5-1.2B-Instruct

by LiquidAI · built on LFM2.5 1.2B Base
#13
Official1.2B
222Kdownloads244likes

An official 1.2B release based on LFM2.5 1.2B Base, intended for everyday chat and writing on a phone. The Q4_K_M file is 0.73 GB.

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

iOS-safe from 4 GB · Android-safe from 4 GB · 0.73 GB download · ~18–30 tok/s (estimate)

Llama-3.2-3B-Instruct

by bartowski · built on Llama 3.2 3B
#15
Official3B
184Kdownloads264likes

An official 3B release based on Llama 3.2 3B, intended for everyday chat and writing on a phone. 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)

gemma-3-4b-it

by unsloth · built on gemma 3 4b pt
#16
Official4BVision
178Kdownloads217likes

An official 4B vision model based on gemma 3 4b pt, made to understand images as well as text. The Q4_K_M file is 2.49 GB.

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

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

LFM3-1.7B-Uncensored

by AtomicChat · built on LFM3 1.7B Base
#87
NewUncensored1.7B
167Kdownloads334likes

LFM3-1.7B-Uncensored is a 1.7B model by AtomicChat of LFM3 1.7B Base, using uncensoring. Languages noted on the card include Chinese, German. The Q4_K_M file is 1.13 GB.

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

iOS-safe from 4 GB · Android-safe from 4 GB · 1.13 GB download · ~18–30 tok/s (estimate)

Huihui-Qwen3.5-4B-abliterated

by huihui-ai · built on Qwen3.5 4B
#72
Uncensored4BVision
158Kdownloads35likes

Huihui-Qwen3.5-4B-abliterated is a 4B model by huihui-ai of Qwen3.5 4B, using abliteration. It can look at a photo or screenshot and answer questions about it. 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)

Phi-4-mini-instruct

by unsloth · built on Phi 4 mini
#18
Official4.2B
120Kdownloads163likes

An official 4.2B release based on Phi 4 mini, intended for everyday chat and writing on a phone. The Q4_K_M file is 2.49 GB.

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

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

Gemma-4-E2B-Uncensored-HauhauCS-Aggressive

by HauhauCS · built on Gemma 4 E2B
#73
Uncensored5.1B · 2.3B activeVision
114Kdownloads382likes

Gemma-4-E2B-Uncensored-HauhauCS-Aggressive is a 5.1B · 2.3B active model by HauhauCS of Gemma 4 E2B, using fine-tuning. It can look at a photo or screenshot and answer questions about it. The Q4_K_M file is 3.45 GB.

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

iOS-safe from 8 GB · Android-safe from 6 GB · 3.45 GB download · ~8–16 tok/s (estimate)

Qwen3.5-2B-Uncensored-HauhauCS-Aggressive

by HauhauCS · built on Qwen3.5 2B
#74
Uncensored2BVision
78Kdownloads185likes

Qwen3.5-2B-Uncensored-HauhauCS-Aggressive is a 2B model by HauhauCS of Qwen3.5 2B, 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 1.27 GB.

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

iOS-safe from 4 GB · Android-safe from 4 GB · 1.27 GB download · ~18–30 tok/s (estimate)

Uncensored4BVision
60Kdownloads31likes

DeepSeek-V4-Pro-Qwen3.5-4B-UNCENSORED-heretic is a 4B model by xtools-at, using heretic, an automated abliteration tool. It can read images and writes out its reasoning before it answers. The Q4_K_M file is 2.78 GB.

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

iOS-safe from 6 GB · Android-safe from 4 GB · 2.78 GB download · ~12–22 tok/s (estimate)

#19
Official7B
55Kdownloads51likes

An official 7B release from bartowski, intended for everyday chat and writing on a phone. The Q4_K_M file is 4.37 GB.

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

iOS-safe from 8 GB · Android-safe from 6 GB · 4.37 GB download · ~8–16 tok/s (estimate)

DeepSeek-R1-Distill-Qwen-1.5B

by bartowski · built on DeepSeek R1 Distill Qwen 1.5B
#20
Official1.5BThinking
50Kdownloads95likes

An official 1.5B reasoning model based on DeepSeek R1 Distill Qwen 1.5B, which works through a problem step by step. The Q4_K_M file is 1.12 GB.

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

iOS-safe from 4 GB · Android-safe from 4 GB · 1.12 GB download · ~18–30 tok/s (estimate)

Spark-X2.6-4B-abliterated-FIT

by SC117 · built on Spark X2.6 4B Base
#89
NewUncensored4BThinking
48Kdownloads44likes

Spark-X2.6-4B-abliterated-FIT is a 4B model by SC117 of Spark X2.6 4B Base, using abliteration. It writes out its reasoning before it answers. Languages noted on the card include Chinese. The Q4_K_M file is 2.7 GB.

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

iOS-safe from 6 GB · Android-safe from 4 GB · 2.7 GB download · ~12–22 tok/s (estimate)

gemma-3n-E2B-it

by unsloth · built on gemma 3n E4B
#22
Official2B
33Kdownloads65likes

An official 2B release based on gemma 3n E4B, intended for everyday chat and writing on a phone. The Q4_K_M file is 3.03 GB.

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

iOS-safe from 6 GB · Android-safe from 4 GB · 3.03 GB download · ~18–30 tok/s (estimate)

LFM2-2.6B

by LiquidAI · built on LFM2 2.6B
#23
Official2.6B
33Kdownloads63likes

An official 2.6B release based on LFM2 2.6B, intended for everyday chat and writing on a phone. The Q4_K_M file is 1.56 GB.

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

iOS-safe from 4 GB · Android-safe from 4 GB · 1.56 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)

Huihui-Qwen3.5-2B-abliterated

by huihui-ai · built on Qwen3.5 2B
#78
Uncensored2BVision
26Kdownloads10likes

Huihui-Qwen3.5-2B-abliterated is a 2B model by huihui-ai of Qwen3.5 2B, using abliteration. It can look at a photo or screenshot and answer questions about it. The Q4_K_M file is 1.27 GB.

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

iOS-safe from 4 GB · Android-safe from 4 GB · 1.27 GB download · ~18–30 tok/s (estimate)

Ministral-3-3B-Instruct-2512

by unsloth · built on Ministral 3 3B Base 2512
#24
Official3BVision
25Kdownloads44likes

An official 3B vision model based on Ministral 3 3B Base 2512, made to understand images as well as text. The Q4_K_M file is 2.15 GB.

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

iOS-safe from 4 GB · Android-safe from 4 GB · 2.15 GB download · ~12–22 tok/s (estimate)

gemma-4-E2B-it-uncensored

by TrevorJS · built on Gemma 4 E2B
#77
Uncensored5.1B · 2.3B active
24Kdownloads73likes

gemma-4-E2B-it-uncensored is a 5.1B · 2.3B active model by TrevorJS of Gemma 4 E2B, using heretic, an automated abliteration tool. The Q4_K_M file is 3.43 GB.

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

iOS-safe from 8 GB · Android-safe from 6 GB · 3.43 GB download · ~8–16 tok/s (estimate)

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)

Qwen3-4B-Thinking-2507

by unsloth · built on Qwen3 4B Thinking 2507
#25
Official4BThinking
18Kdownloads109likes

An official 4B reasoning model based on Qwen3 4B Thinking 2507, which works through a problem step by step. 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)

Dolphin3.0-Llama3.2-3B

by dphn · built on Llama 3.2 3B
#82
Uncensored3B
18Kdownloads38likes

Dolphin3.0-Llama3.2-3B is a 3B model by dphn of Llama 3.2 3B, 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)

Qwen3.5-4B-NSFW-ARA-Heretic-Literotica

by Sinbad-The-Sailor · built on Qwen3.5 4B ARA heresy v2
#2031
NewUncensored4BThinking
15Kdownloads61likes

Qwen3.5-4B-NSFW-ARA-Heretic-Literotica is a 4B model by Sinbad-The-Sailor of Qwen3.5 4B ARA heresy v2, using heretic, an automated abliteration tool. 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)

gemma-4-E2B-it-ultra-uncensored-heretic

by llmfan46 · built on Gemma 4 E2B
#81
Uncensored5.1B · 2.3B activeVision
15Kdownloads41likes

gemma-4-E2B-it-ultra-uncensored-heretic is a 5.1B · 2.3B active model by llmfan46 of Gemma 4 E2B, using heretic, an automated abliteration tool. It can look at a photo or screenshot and answer questions about it. The Q4_K_M file is 3.43 GB.

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

iOS-safe from 8 GB · Android-safe from 6 GB · 3.43 GB download · ~8–16 tok/s (estimate)

SmolLM2-1.7B-Instruct

by HuggingFaceTB · built on SmolLM2 1.7B
#28
Official1.7B
15Kdownloads57likes

An official 1.7B release based on SmolLM2 1.7B, intended for everyday chat and writing on a phone. The Q4_K_M file is 1.06 GB.

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

iOS-safe from 4 GB · Android-safe from 4 GB · 1.06 GB download · ~18–30 tok/s (estimate)

MiniCPM5-2B-heretic-abliterated

by Abiray · built on MiniCPM5 2B
#80
Uncensored2B
14Kdownloads45likes

MiniCPM5-2B-heretic-abliterated is a 2B model by Abiray of MiniCPM5 2B, using fine-tuning. Languages noted on the card include Chinese. The Q4_K_M file is 1.56 GB.

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

iOS-safe from 4 GB · Android-safe from 4 GB · 1.56 GB download · ~18–30 tok/s (estimate)

Gemma-3-1B-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking

by Andycurrent · built on gemma 3 1b pt
#93
NewUncensored1BThinking
13Kdownloads169likes

Gemma-3-1B-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking is a 1B model by Andycurrent of gemma 3 1b pt, using heretic, an automated abliteration tool. It writes out its reasoning before it answers. The Q4_K_M file is 0.81 GB.

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

iOS-safe from 4 GB · Android-safe from 4 GB · 0.81 GB download · ~25–45 tok/s (estimate)

Phi-4-mini-reasoning

by unsloth · built on Phi 4 mini reasoning
#29
Official4.2BThinking
12Kdownloads87likes

An official 4.2B reasoning model based on Phi 4 mini reasoning, which works through a problem step by step. The Q4_K_M file is 2.49 GB.

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

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

Gemma-3-4B-VL-it-Gemini-Pro-Heretic-Uncensored-Thinking

by DavidAU · built on gemma 3 4b heretic uncensored abliterated Extreme
#100
NewUncensored4BThinkingVision
10Kdownloads80likes

Gemma-3-4B-VL-it-Gemini-Pro-Heretic-Uncensored-Thinking is a 4B model by DavidAU of gemma 3 4b heretic uncensored abliterated Extreme, using heretic, an automated abliteration tool. It can read images and writes out its reasoning before it answers. The Q4_K_M file is 2.49 GB.

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

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

SmolLM3-3B

by unsloth · built on SmolLM3 3B Base
#30
Official3B
7.3Kdownloads37likes

An official 3B release based on SmolLM3 3B Base, intended for everyday chat and writing on a phone. The Q4_K_M file is 1.92 GB.

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

iOS-safe from 4 GB · Android-safe from 4 GB · 1.92 GB download · ~12–22 tok/s (estimate)

Huihui-Qwen3.5-0.8B-abliterated

by huihui-ai · built on Qwen3.5 0.8B
#85
Uncensored0.8BVision
7.1Kdownloads10likes

Huihui-Qwen3.5-0.8B-abliterated is a 0.8B model by huihui-ai of Qwen3.5 0.8B, using abliteration. It can look at a photo or screenshot and answer questions about it. The Q4_K_M file is 0.53 GB.

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

iOS-safe from 4 GB · Android-safe from 4 GB · 0.53 GB download · ~25–45 tok/s (estimate)

Nemotron3-Nano-4B-Uncensored-HauhauCS-Aggressive

by HauhauCS · built on NVIDIA Nemotron 3 Nano 4B
#84
Uncensored4B
6.7Kdownloads48likes

Nemotron3-Nano-4B-Uncensored-HauhauCS-Aggressive is a 4B model by HauhauCS of NVIDIA Nemotron 3 Nano 4B, using fine-tuning. The Q4_K_M file is 2.84 GB.

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

iOS-safe from 6 GB · Android-safe from 6 GB · 2.84 GB download · ~12–22 tok/s (estimate)

LFM2.5-2.6B-Heretic-Abliterated

by Abiray · built on LFM2.5 2.6B
#83
Uncensored2.6B
5.3Kdownloads44likes

LFM2.5-2.6B-Heretic-Abliterated is a 2.6B model by Abiray of LFM2.5 2.6B, using fine-tuning. Languages noted on the card include Japanese, Chinese. The Q4_K_M file is 1.67 GB.

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

iOS-safe from 4 GB · Android-safe from 4 GB · 1.67 GB download · ~12–22 tok/s (estimate)

Huihui-Qwen3-1.7B-abliterated-v2

by huihui-ai · built on Qwen3 1.7B
#86
Uncensored1.7B
4.9Kdownloads1likes

Huihui-Qwen3-1.7B-abliterated-v2 is a 1.7B model by huihui-ai of Qwen3 1.7B, using abliteration. 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)

Crow-4B-Opus-4.6-Distill-Heretic_Qwen3.5

by Crownelius · built on Qwen3.5 4B
#2032
NewUncensored4BThinkingCode
4.3Kdownloads64likes

Crow-4B-Opus-4.6-Distill-Heretic_Qwen3.5 is a 4B model by Crownelius of Qwen3.5 4B, using heretic, an automated abliteration tool. It writes out its reasoning before it answers, and is set up for writing code. 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)

Qwen2.5-Coder-3B-Instruct

by unsloth · built on Qwen2.5 Coder 3B
#31
Official3BCode
3.4Kdownloads22likes

An official 3B coding model based on Qwen2.5 Coder 3B. The Q4_K_M file is 1.93 GB.

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

iOS-safe from 4 GB · Android-safe from 4 GB · 1.93 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)

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)

Qwen3.5-4B-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)

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