IQ4_XS GGUF models

Importance-matrix 4-bit quant, extra small. Small files with good quality for the size. 97368 models have a IQ4_XS file. Sizes run from 1M to 2450B parameters. The longest trained context is 102400K tokens.

Most downloadedNewestLargestLongest contextSmallest
GE
Dark Scarlett v0.3 26B A4B
Gemma · ReadyArt
Params25.2B
Context256K
Q4_K_M16.8 GB
Roleplay
LL
Meta Llama 3.1 70B Instruct
Llama · lmstudio-community
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
PA
MS3.2 PaintedFantasy v4.1 24B
Paintedfantasy · zerofata
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
DE
Deepseek-R1-0528
DeepSeek · unsloth
Params670B
Context160K
Q4_K_M404.9 GB
CodingReasoning
GL
Huihui GLM 4.7 Flash Abliterated
GLM · mradermacher
Params30B
Context198K
Q4_K_M18.1 GB
GGUF
LL
Hermes 3 Llama 3.1 8B
Llama · bartowski
Params8B
Context128K
Q4_K_M4.9 GB
RoleplayTool use
LA
Laguna-S-2.1
Laguna · unsloth
Params118B
Context256K
Q4_K_M73.1 GB
GGUF
MI
minmax
Minmax · Kutches
Params20.1B
Context—
Q4_K_M11.5 GB
GGUF
QW
Qwen3.8 Flash Next IQ4 XS
Qwen · julianmb
Params177B
Context256K
Smallest4.1 GB
GGUF
QW
Suri Qwen 3.8 27B Companion
Qwen · SpaceTimee
Params27.3B
Context256K
Q4_K_M16.5 GB
Vision
QW
Signal 3.8 27B
Qwen · agentionai
Params27.3B
Context—
Q4_K_M17.0 GB
GGUF
SM
Smollm3-3B
SmolLM · unsloth
Params3.08B
Context64K
Q4_K_M1.9 GB
GGUF
NE
Nvidia-Nemotron-3-Nano-Omni-30B-A3B-Reasoning
Nemotron · unsloth
Params31.6B
Context1024K
Q4_K_M23.9 GB
ReasoningVision
LL
4yo1 llama3 pre1 pre2 ds ins2 lora3
Llama · RichardErkhov
Params200M
Context—
Q4_K_M0.0 GB
GGUF
GE
Gemma 4 31B It Heretic
Gemma · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
Coding
AL
Source Hf Aliceai T5 35b A0.6B
Aliceai · ngquocvinh
Params34.6B
Context128K
Q4_K_M21.0 GB
Coding
QW
Qwen3 VL 8B NSFW Caption V4.5
Qwen · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
Tool useVision
QW
Huihui Qwen3 4B Abliterated v2
Qwen · mradermacher
Params4B
Context40K
Q4_K_M2.5 GB
GGUF
LL
Meta Llama 3.1 8B Instruct Abliterated
Llama · bartowski
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
QW
Qwen3 VL 32B Instruct
Qwen · bartowski
Params32.8B
Context256K
Q4_K_M19.8 GB
Vision
VI
MN Violet Lotus 12B
Violet · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
Roleplay
MI
Ministral-3-8B-Reasoning-2512
Mistral · unsloth
Params8.49B
Context256K
Q4_K_M5.2 GB
ReasoningVision
OM
Omega Arsenal 12B
Omega · ReadyArt
Params11.9B
Context256K
Q4_K_M7.4 GB
ReasoningRoleplayTool use
MI
MiniCPM-V-4.7-1B
MiniCPM · AtomicChat
Params1.01B
Context256K
Q4_K_M0.7 GB
ReasoningTool useVision
QW
Qwen2.5 VL 7B Instruct Unredacted MAX
Qwen · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
Vision
QW
Qwen3 30B A3B Abliterated Erotic
Qwen · mradermacher
Params30.5B
Context40K
Q4_K_M18.6 GB
GGUF
OC
Occamy 1.0 Abliterated
Occamy · SC117
Params34.7B
Context256K
Q4_K_M16.5 GB
ReasoningVision
QW
Qwen3-4B-Thinking-2507
Qwen · unsloth
Params4B
Context256K
Q4_K_M2.5 GB
Reasoning
GO
Goetia 26B A4B v1.7
Goetia · mradermacher
Params26B
Context256K
Q4_K_M17.2 GB
Roleplay
LF
LFM2.5-24B-A2B
Lfm · NANI-Nithin
Params24B
Context128K
Q4_K_M14.5 GB
GGUF

Other quants

Keep browsing