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 24B A2B Abliterated
Lfm · mradermacher
Params24B
Context128K
Q4_K_M14.5 GB
ReasoningTool use
ST
L3-8B-Stheno-v3.2
Stheno · DavidAU
Params8B
Context8K
Q4_K_M4.9 GB
Roleplay
DE
Qwen3 30B A3B Deepseek Distill Instruct 2507
DeepSeek · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
GGUF
MI
MixTaoTruthful-13B-slerp
Mixtaotruthful · mradermacher
Params12.9B
Context32K
Q4_K_M7.8 GB
GGUF
ST
Starcoder2 15b
StarCoder · mradermacher
Params16B
Context16K
Q4_K_M9.9 GB
Coding
DE
Qwen2.5 MOE 2X1.5B DeepSeek Uncensored Censored 4B
DeepSeek · DavidAU
Params4.1B
Context128K
Q4_K_M2.5 GB
Reasoning
LL
Meta Llama 3 8B Instruct GGUF Imatrix smashed
Llama · PrunaAI
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
BO
Borealis Open 12b
Borealis · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
GGUF
LF
LFM2.5 8B A1B Hermes Agentic Coder Abliterated v3
Lfm · mradermacher
Params8.47B
Context125K
Q4_K_M5.2 GB
CodingReasoningTool use
LU
Lumimaid Magnum v4 12B
Lumimaid · bartowski
Params12.2B
Context128K
Q4_K_M7.5 GB
GGUF
QW
DPO Trained Qwen2.5 Python Coder 7B
Qwen · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
Coding
CH
Chaotic Order 24B V5
Chaotic · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
QW
DarkIdol Qwen3.8 27B v1.1
Qwen · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
ReasoningRoleplayVision
QW
Qwen3.5 2B Uncensored Zero Refusal SOMA
Qwen · mradermacher
Params1.88B
Context256K
Q4_K_M1.3 GB
RoleplayVision
LL
CodeLlama 70b Hf
Llama · mradermacher
Params69B
Context16K
Q4_K_M41.4 GB
Coding
QW
Qwen3 Coder Next Uncensored Heretic
Qwen · mradermacher
Params79.7B
Context256K
Q4_K_M48.5 GB
Coding
MI
Tamil-Mistral-7B-v0.1
Mistral · RichardErkhov
Params7.39B
Context32K
Q4_K_M4.5 GB
GGUF
DE
Deacon-34B
Deacon · mradermacher
Params34.4B
Context4K
Q4_K_M20.7 GB
GGUF
DA
Dark Scarlett 27B v2.0
Dark · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
RoleplayVision
FA
FashionGPT 70B V1.2 i1
Fashiongpt · mradermacher
Params69B
Context4K
Q4_K_M41.4 GB
GGUF
OR
Ornith 1.0 397B
Ornith · unsloth
Params397B
Context256K
Q4_K_M245.0 GB
GGUF
MI
models--mistralai--Mixtral-8x22B-Instruct-v0.1
Mistral · MaziyarPanahi
Params141B
Context64K
Q4_K_M85.6 GB
GGUF
NE
Nemotron 3.5 Embed 8B BF16
Nemotron · W4D
Params7.95B
Context256K
Q4_K_M4.9 GB
EmbeddingVision
RE
REBEL-OpenChat-3.5
Rebel · mradermacher
Params7.24B
Context8K
Q4_K_M4.4 GB
GGUF
MI
Sakura MiniCPM V 4.7 1B Uncensored
MiniCPM · webmp3
Params1.01B
Context256K
Q4_K_M0.7 GB
Vision
MU
Muse Glimmer 30B AZ Focus
Muse · mradermacher
Params27.9B
Context128K
Q4_K_M16.9 GB
ReasoningTool use
QW
Qwen2.5 Coder 7B Instruct Abliterated
Qwen · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
Coding
QW
Qwen3 14B NSFW FDA
Qwen · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
GGUF
GP
SpaceQA Gpt Oss 20b
gpt-oss · mradermacher
Params20.9B
Context128K
Q4_K_M15.8 GB
Tool use
LF
LFM2 24B A2B
Lfm · bartowski
Params23.8B
Context125K
Q4_K_M14.4 GB
GGUF

Other quants

Keep browsing