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
AS
AstaBrief_8B
Astabrief · mradermacher
Params8.2B
Context40K
Q4_K_M5.0 GB
GGUF
QW
Qwen3.6 35B A3B Uncensored Heretic Native MTP Preserved
Qwen · mradermacher
Params35.5B
Context256K
Q4_K_M21.7 GB
GGUF
SP
Spark X2.6 4B Uncensored GSQ RCO
Spark · abenzerps
Params4.11B
Context1024K
Smallest1.6 GB
ReasoningTool use
GE
Gemma 4 12B OBLITERATED
Gemma · mradermacher
Params11.9B
Context128K
Q4_K_M7.4 GB
GGUF
RE
ReflectionCoder-CL-34B
Reflectioncoder · mradermacher
Params33.7B
Context16K
Q4_K_M20.2 GB
Coding
QW
Qwen3.8 27B
Qwen · batiai
Params27B
Context256K
Q4_K_M16.5 GB
GGUF
QW
Qwen3.6 Fallen Fabulist 35B A3B Heretic
Qwen · mradermacher
Params35.5B
Context256K
Q4_K_M21.7 GB
RoleplayVision
QW
Qwen3.8 4B Heretic
Qwen · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
GGUF
GE
Gemma 4 E4B It Ultra Uncensored Heretic
Gemma · mradermacher
Params7.52B
Context128K
Q4_K_M5.3 GB
ReasoningTool useVision
GR
granite 20b functioncalling i1
Granite · mradermacher
Params20B
Context8K
Q4_K_M12.8 GB
GGUF
NA
Nanbeige4.3 33B cybersec abliterated
Nanbeige · FRENCHFAKER
Params33.1B
Context512K
Q4_K_M20.1 GB
ReasoningTool use
PY
Pythia 410m Deduped
Pythia · mradermacher
Params405M
Context2K
Q4_K_M0.3 GB
GGUF
QW
Qwen3.8 2B Distill Heretic
Qwen · mradermacher
Params1.88B
Context256K
Q4_K_M1.3 GB
ReasoningTool use
MI
Voxtral Small 24B 2507
Mistral · bartowski
Params23.6B
Context128K
Q4_K_M14.3 GB
Vision
DE
Qwen2.5 32B
DeepSeek · bartowski
Params32.8B
Context128K
Q4_K_M19.9 GB
Reasoning
QW
Qwen3 8B Socratic SFT
Qwen · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
GGUF
GP
Gpt Oss 20b Abliterated
gpt-oss · mradermacher
Params20.9B
Context128K
Q4_K_M15.8 GB
GGUF
GE
Skaldic Gemma 4 E4B
Gemma · mradermacher
Params7.46B
Context128K
Q4_K_M5.3 GB
GGUF
QW
Qwen2-1.5B-Instruct
Qwen · legraphista
Params1.54B
Context32K
Smallest0.4 GB
GGUF
JA
Jais-3-7B
Jais · mradermacher
Params9B
Context512K
Q4_K_M5.6 GB
Reasoning
QW
Qwen3 32B Abliterated
Qwen · mradermacher
Params32.8B
Context40K
Q4_K_M19.8 GB
GGUF
UM
Umievo-itr012-Gleipnir-7B
Umievo · mmnga
Params7.24B
Context8K
Q4_K_M4.4 GB
GGUF
KI
Kisoku 1.6b Chat
Kisoku · mradermacher
Params1.6B
Context128K
Q4_K_M1.0 GB
Tool use
HU
Hunyuan 1.8B Instruct
Hunyuan · bartowski
Params1.79B
Context256K
Q4_K_M1.1 GB
GGUF
ZA
Zaire 12B v0.1
Zaire · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
ReasoningTool use
GR
Granite 3b Code Base 128k
Granite · RichardErkhov
Params3.48B
Context125K
Q4_K_M2.1 GB
Coding
GE
Gemma 4 31B It Uncensored Heretic
Gemma · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
GGUF
QW
Huihui Qwen3.6 35B A3B Claude 4.7 Opus Abliterated
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningVision
GE
Gemma 4 E4B It Apostate
Gemma · mradermacher
Params8.13B
Context128K
Q4_K_M5.0 GB
ReasoningTool use
QI
QiMing Holos Plus 8B
Qiming · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
GGUF

Other quants

Keep browsing