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
JI
jina embeddings v5 omni nano classification
Jina · jinaai
Params212M
Context8K
Q4_K_M0.2 GB
EmbeddingVision
QW
Qwen3 Coder 42B A3B Instruct TOTAL RECALL MASTER CODER M 1million Ctx
Qwen · mradermacher
Params42.4B
Context1024K
Q4_K_M25.7 GB
CodingReasoning
LL
Fireball Alpaca Llama3.1 8B Philos i1
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
TI
TigerLLM 12B It
Tigerllm · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
GGUF
NA
Nanonets OCR S
Nanonets · prithivMLmods
Params3.1B
Context125K
Q4_K_M1.9 GB
Vision
SO
solar merge v1.0 i1
Solar · mradermacher
Params19.2B
Context4K
Q4_K_M11.6 GB
GGUF
CH
chronos007 70b i1
Chronos · mradermacher
Params69B
Context4K
Q4_K_M41.7 GB
Roleplay
WI
WizardMath 7B V1.0
Wizardmath · mradermacher
Params6.74B
Context2K
Q4_K_M4.1 GB
GGUF
QW
Qwen3.5 4B Claude 4.6 OS Auto Variable HERETIC UNCENSORED THINKING
Qwen · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningRoleplay
QW
qwen3.5 35b a3b compacted
Qwen · cahlen
Params23.5B
Context256K
Q4_K_M14.4 GB
GGUF
QI
QiMing CognitiveForge 14B
Qiming · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
GGUF
QW
PocketWeights Qwen2.5 14B Coder Creative
Qwen · mradermacher
Params14.8B
Context986K
Q4_K_M9.0 GB
Coding
NU
NuminaMath-7B-TIR
Numinamath · legraphista
Params6.91B
Context4K
Smallest1.7 GB
GGUF
QW
Qwen3 53B A3B TOTAL RECALL v1.4 128k
Qwen · mradermacher
Params53B
Context128K
Q4_K_M32.1 GB
CodingReasoning
FO
Foresight 32B
Foresight · mradermacher
Params32.8B
Context40K
Q4_K_M19.8 GB
GGUF
BE
Behemoth X 123B v2
Behemoth · bartowski
Params123B
Context128K
Q4_K_M73.2 GB
GGUF
HA
Hamanasu 15B Adventure i1
Hamanasu · mradermacher
Params14.7B
Context16K
Q4_K_M8.9 GB
Roleplay
LL
Llm Jp 3.1 1.8b
Llm · mmnga
Params1.87B
Context4K
Q4_K_M1.2 GB
GGUF
GR
Granite 20b Code Base 8k
Granite · mradermacher
Params20B
Context8K
Q4_K_M12.8 GB
Coding
AP
Apertus 70B Instruct 2509
Apertus · bartowski
Params70.6B
Context64K
Q4_K_M43.7 GB
GGUF
CO
Yi Coder 9B
Coder · mradermacher
Params8.83B
Context128K
Q4_K_M5.3 GB
Coding
MI
Devstral Small 2505 Abliterated
Mistral · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
Coding
EU
L3-70B-Euryale-v2.1
Euryale · InferenceIllusionist
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
HU
Huihui4 8B A4B v2
Huihui · mradermacher
Params8.1B
Context256K
Q4_K_M5.4 GB
GGUF
GE
Gemma 3 12b It Vl GLM 4.7 Flash Polaris Thinking Heretic Uncensored
Gemma · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
ReasoningVision
QW
Qwen3.8 27B OBLITERATED 12GB
Qwen · cognitivers
Params27.3B
Context—
Smallest0.0 GB
GGUF
LL
llama-3-Nephilim-v2-8B
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
PH
Phi 3 mini 4k instruct imatrix
Phi · duyntnet
Params3.82B
Context4K
Q4_K_M2.4 GB
GGUF
LL
Llama 3.2 8X3B GATED MOE NEO Reasoning Dark Champion uncensored 18.4B IMAT
Llama · DavidAU
Params18.4B
Context128K
Q4_K_M11.3 GB
ReasoningRoleplay
HA
Hathor v4.6 i1
Hathor · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF

Other quants

Keep browsing