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
QW
Qwen2.5 7B
Qwen · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
GGUF
QW
Qwen2.5 3B Instruct Abliterated
Qwen · mradermacher
Params3.09B
Context32K
Q4_K_M1.9 GB
GGUF
GR
Granite 8b Code Base 4k
Granite · RichardErkhov
Params8.05B
Context4K
Q4_K_M4.9 GB
Coding
WI
WizardCoder 33B V1.1
Wizardcoder · mradermacher
Params33.3B
Context16K
Q4_K_M19.9 GB
Coding
ZE
zed industries zeta 2
Zeta · bartowski
Params8.25B
Context32K
Q4_K_M5.2 GB
GGUF
QW
Qwen3 4B Base
Qwen · mradermacher
Params4B
Context32K
Q4_K_M2.5 GB
GGUF
MI
Dolphin3.0 Mistral 24B
Mistral · mradermacher
Params23.6B
Context32K
Q4_K_M14.3 GB
CodingTool use
OL
open r1 OlympicCoder 7B
Olympiccoder · bartowski
Params7.62B
Context32K
Q4_K_M4.7 GB
CodingReasoning
VI
Vinci MLE 8B 1.0
Vinci · mradermacher
Params8.79B
Context128K
Q4_K_M5.3 GB
Tool use
CU
CursorCore QW2.5 1.5B i1
Cursorcore · mradermacher
Params1.54B
Context32K
Q4_K_M1.0 GB
Coding
GL
Huihui GLM 4.6V Flash Abliterated
GLM · mradermacher
Params9.4B
Context128K
Q4_K_M6.2 GB
GGUF
QW
Bella Bartender Qwen3 1.7b
Qwen · mradermacher
Params1.72B
Context40K
Q4_K_M1.1 GB
ReasoningTool use
GM
GmshNet 8B v0.1
Gmshnet · hexera-org
Params7.62B
Context32K
Q4_K_M4.7 GB
CodingReasoning
CH
ChemLLM 20B Chat DPO
Chemllm · mradermacher
Params19.9B
Context32K
Q4_K_M12.0 GB
GGUF
QW
Models Qwen Qwen2 Math 7B Instruct
Qwen · MaziyarPanahi
Params7.62B
Context4K
Q4_K_M4.7 GB
GGUF
QW
Qwen3.8 27B full Uncensored
Qwen · 0xSojalSec
Params27.3B
Context256K
Q4_K_M16.8 GB
Vision
GE
Gemma 4 19B A4B It The DECKARD Heretic Uncensored Thinking
Gemma · mradermacher
Params18.4B
Context256K
Q4_K_M12.3 GB
CodingReasoningRoleplay
QW
Qwen3.8 27B TURBO MTP
Qwen · nimbowz
Params27B
Context256K
Q4_K_M18.0 GB
CodingReasoningRoleplay
NE
NeuralStar_FusionWriter_4x7b
Neuralstar · mradermacher
Params24.2B
Context32K
Q4_K_M14.6 GB
GGUF
LL
Replete Coder V2 Llama 3.1 8b
Llama · bartowski
Params8B
Context128K
Q4_K_M4.9 GB
Coding
MI
Chinese Mistral 7B Instruct v0.1
Mistral · RichardErkhov
Params7.5B
Context32K
Q4_K_M4.5 GB
GGUF
GP
Gpt Neox 20b
Gpt · mradermacher
Params20.6B
Context2K
Q4_K_M13.1 GB
GGUF
LL
Llama3.3 8B Instruct Thinking Claude 4.5 Opus High Reasoning
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
ReasoningRoleplay
RP
RPBizkit v11 12B Base
Rpbizkit · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
YI
Yi 1.5 9B Chat 16K Abliterated
Yi · mradermacher
Params8.83B
Context16K
Q4_K_M5.3 GB
GGUF
HO
K2-Horizon-375B-A23B
Horizon · bartowski
Params379B
Context512K
Q4_K_M237.8 GB
GGUF
SP
Spark X2.6 1.7B
Spark · mradermacher
Params1.71B
Context1024K
Q4_K_M1.1 GB
ReasoningTool use
WI
WizardCoder Python 34B V1.0 i1
Wizardcoder · mradermacher
Params33.7B
Context16K
Q4_K_M20.2 GB
Coding
QW
Qwen 3.8 27b Abliterated
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
GGUF
MI
Mistral Nemo Instruct 2407 Absolute Heresy
Mistral · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
GGUF

Other quants

Keep browsing