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
Llama3.2 24B A3B II Dark Champion INSTRUCT Heretic Abliterated Uncensored
Llama · mradermacher
Params18B
Context128K
Q4_K_M11.1 GB
Roleplay
AT
Atom 80b
Atom · mradermacher
Params80B
Context256K
Q4_K_M48.4 GB
Reasoning
NE
Nemotron H 47B Reasoning 128K
Nemotron · bartowski
Params47B
Context1024K
Q4_K_M28.2 GB
Reasoning
MI
Ministral 3 3B Reasoning UNCENSORED Heretic
Mistral · mradermacher
Params3.43B
Context256K
Q4_K_M2.1 GB
Reasoning
YI
Capybara Tess Yi 34B 200K i1
Yi · mradermacher
Params34.4B
Context195K
Q4_K_M20.7 GB
GGUF
OM
OmniDimen 2 20B Emotion
Omnidimen · mradermacher
Params20.9B
Context128K
Q4_K_M15.8 GB
GGUF
IC
IceEspressoRPv2 7b i1
Iceespressorpv · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
AT
Athena v4 i1
Athena · mradermacher
Params13B
Context4K
Q4_K_M8.1 GB
GGUF
GR
GritLM 8x7B KTO i1
Gritlm · mradermacher
Params46.7B
Context32K
Q4_K_M28.4 GB
GGUF
MI
Codestral-22B-v0.1-abliterated-v3
Mistral · mradermacher
Params22.2B
Context32K
Q4_K_M13.3 GB
Coding
DE
DeepSeek-Coder-V2-Lite-Instruct
DeepSeek · mradermacher
Params15.7B
Context160K
Q4_K_M10.4 GB
Coding
QW
X Coder SFT Qwen2.5 7B
Qwen · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
Coding
QW
Qwen2.5 7B Instruct Abliterated
Qwen · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
LL
Rombos LLM 70b Llama 3.3
Llama · bartowski
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
LL
Llama3.1 8B PlumCode
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
Coding
PH
Phi 3 mini 128k instruct
Phi · mmnga
Params3.82B
Context128K
Q4_K_M2.4 GB
GGUF
EC
Eclipsed Phoenix 26B A4B
Eclipsed · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
Roleplay
QW
Qwen3.5 9B Claude 4.6 HighIQ THINKING HERETIC UNCENSORED
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningRoleplay
PH
Phi 3.5 Mini instruct_Uncensored
Phi · mradermacher
Params3.82B
Context128K
Q4_K_M2.4 GB
GGUF
BA
BananaMind Translate V3.5 Pro
Bananamind · mradermacher
Params7.46B
Context128K
Q4_K_M5.3 GB
GGUF
LA
30B Lazarus i1
Lazarus · mradermacher
Params32.5B
Context2K
Q4_K_M19.6 GB
GGUF
KI
Kisoku 1.6b
Kisoku · mradermacher
Params1.6B
Context128K
Q4_K_M1.0 GB
Coding
QW
Qwen3 30B A3B Thinking 2507 Art
Qwen · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
Reasoning
OC
OculusMind ToolCall 8B v2
Oculusmind · mradermacher
Params8.49B
Context256K
Q4_K_M5.2 GB
Tool use
MO
Moistral-11B-v5b
Moistral · mradermacher
Params10.7B
Context8K
Q4_K_M6.5 GB
GGUF
NO
Norobara ZLoss 8x7B i1
Norobara · mradermacher
Params46.7B
Context32K
Q4_K_M28.6 GB
GGUF
QW
Huihui Qwen3 Omni 30B A3B Thinking Abliterated
Qwen · mradermacher
Params30.5B
Context64K
Q4_K_M18.6 GB
Reasoning
QW
Qwen3 30B A3B Instruct 2507 Heretic
Qwen · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
GGUF
DE
Deepseek-R1
DeepSeek · unsloth
Params670B
Context160K
Q4_K_M404.7 GB
CodingReasoning
GE
Gemma 4 31b It Heretic Ara
Gemma · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
GGUF

Other quants

Keep browsing