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
BE
BeaverAI NeMoist 21B v1a
Beaverai · RichardErkhov
Params21B
Context—
Q4_K_M0.0 GB
GGUF
QW
Qwen3.8 27B Heretic JP Roleplay NSFW DanbooruTags
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
Roleplay
MI
models--mistralai--mathstral-7B-v0.1
Mistral · MaziyarPanahi
Params7.25B
Context32K
Q4_K_M4.4 GB
GGUF
QW
Qwen3.8 27B TWIN TURBO Fable Cold Fusion 709 ULTRA HERETIC Uncensored NM DAU NEO MTP
Qwen · DavidAU
Params27B
Context256K
Q4_K_M18.0 GB
CodingReasoningRoleplay
QW
Qwen3 VL 32B Instruct ultra uncensored heretic H3
Qwen · nif0
Params25.2B
Context256K
Q4_K_M14.9 GB
Vision
LL
Models Meta Llama Meta Llama 3.1 70B Instruct
Llama · MaziyarPanahi
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
LL
Llama-4-Scout-17B-16E-Instruct
Llama · unsloth
Params108B
Context10240K
Q4_K_M65.4 GB
Vision
QW
Qwen3.5 35B A3B
Qwen · bartowski
Params35.5B
Context256K
Q4_K_M22.3 GB
Vision
OR
Ornith 1.5 9B
Ornith · AtomicChat
Params8.95B
Context256K
Smallest2.8 GB
ReasoningTool useVision
GL
Glm-4.6V-Flash
GLM · unsloth
Params9.4B
Context128K
Q4_K_M6.2 GB
Vision
QW
models--Qwen--Qwen2-7B-Instruct
Qwen · MaziyarPanahi
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
OR
Orion 26B A4B v1.1
Orion · bartowski
Params25.2B
Context256K
Q4_K_M18.0 GB
Vision
TR
Translategemma 4b It
Translategemma · mradermacher
Params3.88B
Context128K
Q4_K_M2.5 GB
Vision
QW
Qwen2.5 Coder 1.5B Instruct
Qwen · bartowski
Params1.54B
Context32K
Q4_K_M1.0 GB
Coding
MI
Models Mistralai Mistral Small Instruct 2409
Mistral · MaziyarPanahi
Params22.2B
Context32K
Q4_K_M13.3 GB
GGUF
QW
Qwen2.5 Coder 14B Instruct Abliterated
Qwen · bartowski
Params14.8B
Context32K
Q4_K_M9.0 GB
Coding
SA
Sakura GalTransl 7B v3.7
Sakura · SakuraLLM
Params7.72B
Context128K
Smallest4.3 GB
GGUF
DE
Deepseek-R1-Distill-Llama-70B
DeepSeek · unsloth
Params70.6B
Context128K
Q4_K_M42.5 GB
Reasoning
QW
Qwen3.8 Flash Next
Qwen · agentionai
Params177B
Context256K
Q4_K_M94.5 GB
GGUF
GE
Gemma-4-E2B-It
Gemma · ente-ai
Params4.65B
Context128K
Q4_K_M3.1 GB
Vision
NE
Nemotron-3-Nano-30B-A3B
Nemotron · unsloth
Params31.6B
Context1024K
Q4_K_M24.6 GB
Coding
GE
Gemma-3-27B-It
Gemma · unsloth
Params27B
Context128K
Q4_K_M16.5 GB
Vision
QW
Qwen3.6-27B-Uncensored-HauhauCS-Balanced
Qwen · HauhauCS
Params27B
Context256K
Smallest10.0 GB
Vision
GE
Gemma 3 4b It
Gemma · bartowski
Params3.88B
Context128K
Q4_K_M2.5 GB
Vision
QW
Huihui Qwen3.6 35B A3B Abliterated
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
GGUF
LL
models--fireworks-ai--firefunction-v2
Llama · MaziyarPanahi
Params70.6B
Context8K
Q4_K_M42.5 GB
Tool use
SM
SmolLM3 3B
SmolLM · bartowski
Params3.08B
Context64K
Q4_K_M1.9 GB
GGUF
LL
Llama 3.3 70B Instruct Abliterated
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
NE
NVIDIA Nemotron 3.5 Lightning 30B A3B
Nemotron · bartowski
Params32.9B
Context1024K
Q4_K_M25.5 GB
GGUF
LL
DarkIdol Llama 3.1 8B Instruct 1.2 Uncensored
Llama · bartowski
Params8B
Context128K
Q4_K_M4.9 GB
Roleplay

Other quants

Keep browsing