IQ2_XXS GGUF models

Importance-matrix 2-bit quant. Extreme compression with a large quality cost. 26647 models have a IQ2_XXS file. Sizes run from 2M to 2780B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
LL
Lexi Llama 3 8B Uncensored
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
GE
MR_MARTIN_31b_V1.0_Gemma 4 Base Ftp
Gemma · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
Vision
LL
Llama 3.1 Minitron 4B Width Base
Llama · ThomasBaruzier
Params4.51B
Context128K
Q4_K_M2.8 GB
GGUF
PH
Phi 3 medium 128k instruct imatrix
Phi · duyntnet
Params14B
Context128K
Q4_K_M8.6 GB
GGUF
LO
Loopl Vl 2b
Loopl · mradermacher
Params1.72B
Context256K
Q4_K_M1.1 GB
Tool useVision
LL
Asclepius-Llama3-8B
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
AS
ASTRA 14B Thinking v1
Astra · mradermacher
Params14.8B
Context130K
Q4_K_M9.0 GB
ReasoningTool use
FA
Falcon H1 1.5B Instruct
Falcon · tiiuae
Params1.55B
Context128K
Q4_K_M0.9 GB
GGUF
QW
Qwen3 0.6B BrowserAgent
Qwen · mradermacher
Params596M
Context40K
Q4_K_M0.4 GB
GGUF
NU
NuMarkdown-8B-Thinking
Numarkdown · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
ReasoningVision
LL
dolphin-2.9.1-llama-3-70b
Llama · legraphista
Params70.6B
Context8K
Smallest15.3 GB
CodingTool use
PA
PathfinderAI5.0 i1
Pathfinderai · mradermacher
Params32.8B
Context32K
Q4_K_M19.9 GB
ReasoningTool use
TH
TherapyBeagle 11B v2 i1
Therapybeagle · mradermacher
Params10.7B
Context32K
Q4_K_M6.5 GB
GGUF
MI
internlm2-math-plus-mixtral8x22b
Mistral · legraphista
Params141B
Context64K
Smallest29.6 GB
GGUF
NE
Next 8b
Next · mradermacher
Params8.19B
Context128K
Q4_K_M5.0 GB
Reasoning
GR
Grok Oss Thanatos
Grok · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
QW
Qwen3.5 9B Claude 4.6 Opus Deckard V4.2 Uncensored Heretic Thinking
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningRoleplay
QW
Qwen2.5 0.5B Instruct 3MPER0RR Abliterated
Qwen · mradermacher
Params494M
Context32K
Q4_K_M0.4 GB
GGUF
DO
Dots.Llm1.Inst
Dots · unsloth
Params143B
Context32K
Q4_K_M94.5 GB
GGUF
QW
Qwen3.5 35B A3B Heretic Opus 4.6 Distilled
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool use
QW
Qwen3 42B A3B Spock Brutal Recall Instruct
Qwen · mradermacher
Params42.4B
Context256K
Q4_K_M25.7 GB
CodingReasoning
KA
karakuri lm 8x7b chat v0.1
Karakuri · mmnga
Params46.7B
Context32K
Smallest9.8 GB
GGUF
QW
Qwen3 42B A3B 2507 Thinking Abliterated Uncensored TOTAL RECALL v2 Medium MASTER CODER
Qwen · mradermacher
Params42.4B
Context256K
Q4_K_M25.7 GB
CodingReasoning
DE
DeepSeek R1 Distill Qwen 32B Uncensored
DeepSeek · mradermacher
Params32.8B
Context128K
Q4_K_M19.8 GB
Reasoning
GE
Gemma-2-9B-It-SPPO-Iter3
Gemma · mradermacher
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
YI
Yi-1.5-9B-32K
Yi · mradermacher
Params8.83B
Context32K
Q4_K_M5.3 GB
GGUF
MI
Dolphin Mistral 24B Venice Edition Heretic
Mistral · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
JA
Jais Adapted 7b Chat
Jais · mradermacher
Params7B
Context4K
Q4_K_M4.3 GB
Coding
PH
Phi 3.5 MoE Instruct
Phi · bartowski
Params41.9B
Context128K
Q4_K_M25.3 GB
Coding
DE
DeepSeek V4.1 Flash 1017 GSQ RCO
DeepSeek · taurusduan
Params197B
Context—
Smallest110.6 GB
GGUF

Other quants

Keep browsing