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
LF
LFM2.5 VL 3B Uncensored
Lfm · SC117
Params2.7B
Context125K
Q4_K_M1.7 GB
Vision
QW
Qwen3 14B ARPO DeepSearch
Qwen · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
Tool use
MY
Mythos v2 9b
Mythos · fableforge-ai
Params9.2B
Context256K
Q4_K_M5.8 GB
Tool use
HO
Holo 3.1 4B
Holo · mradermacher
Params4.84B
Context256K
Q4_K_M3.1 GB
ReasoningTool useVision
NE
Nemotron3-Nano-4B-Uncensored-HauhauCS-Aggressive
Nemotron · HauhauCS
Params3.97B
Context1024K
Q4_K_M2.8 GB
GGUF
TO
tokyotech llm Swallow MS 7b instruct v0.1
Tokyotech · mmnga
Params7.33B
Context4K
Q4_K_M4.4 GB
GGUF
QW
qwen image edit plus
Qwen · calcuis
Params14.3B
Context—
Q4_K_M11.7 GB
GGUF
XO
Xor 26B A4B
Xor · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
GGUF
PR
Promethean Dawn 26B A4B
Promethean · mradermacher
Params26B
Context256K
Q4_K_M17.2 GB
Roleplay
QW
Qwen3.5 9B Cold Fusion GAIN v1.0 Uncensored Heretic NEO MAX Imatrix
Qwen · DavidAU
Params8.95B
Context256K
Q4_K_M6.8 GB
CodingReasoningRoleplay
EM
Source Hf Embeddinggemma 2
Embeddinggemma · ngquocvinh
Params271M
Context256K
Q4_K_M0.2 GB
EmbeddingVision
LF
LFM2.5 24B A2B Uncensored Heretic
Lfm · mradermacher
Params24B
Context128K
Q4_K_M14.5 GB
GGUF
WI
WizardLM 30B Uncensored Guanaco SuperCOT 30b i1
Wizardlm · mradermacher
Params32.5B
Context2K
Q4_K_M19.6 GB
GGUF
JA
Jais-3-32B
Jais · mradermacher
Params34.8B
Context512K
Q4_K_M21.1 GB
Reasoning
QW
Qwen2.5 VL 32B Instruct Abliterated
Qwen · mradermacher
Params32.8B
Context125K
Q4_K_M19.9 GB
Vision
GE
Gemma 4 E2B It Heretic Ara
Gemma · mradermacher
Params4.65B
Context128K
Q4_K_M3.4 GB
GGUF
NA
VisionPsy Nano 460M Flash GGUFs
Nanovlm · qvac
Params409M
Context8K
Q4_K_M0.3 GB
Vision
QW
JetBrains Qwen3.8 3.6 27B Blend
Qwen · bartowski
Params27.3B
Context256K
Q4_K_M17.4 GB
Vision
DE
Deepseek-V3.2
DeepSeek · unsloth
Params670B
Context160K
Q4_K_M405.4 GB
GGUF
SA
Sabi Noema
Sabi · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
Tool use
OL
OLMo 2 1124 13B Instruct
OLMo · bartowski
Params13.7B
Context4K
Q4_K_M8.4 GB
GGUF
QW
JonathanColetti Qwen3.8 27B Uncensored
Qwen · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
Vision
QW
Qwen2 VL 7B Instruct
Qwen · bartowski
Params7.62B
Context32K
Q4_K_M4.7 GB
Vision
QW
Qwen2 Audio 7B Instruct
Qwen · mradermacher
Params7.75B
Context8K
Q4_K_M4.8 GB
Vision
ER
Ernie-4.5-21B-A3B-Pt
Ernie · unsloth
Params21.8B
Context128K
Q4_K_M13.3 GB
GGUF
MI
Devstral-2-123B-Instruct-2512
Mistral · unsloth
Params125B
Context256K
Q4_K_M74.9 GB
Coding
PH
Phi 3.1 mini 4k instruct
Phi · bartowski
Params3.82B
Context4K
Q4_K_M2.4 GB
Coding
GL
GLM 4.7 Flash Derestricted
GLM · mradermacher
Params30B
Context198K
Q4_K_M18.1 GB
GGUF
HE
HERO 35B A3B
Hero · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
GGUF
LL
Huihui Mistral Small 3.2 24B Instruct 2506 Abliterated Llamacppfixed
Llama · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
Vision

Other quants

Keep browsing