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
GE
Gemma 3 Uncensored_v2 Merged
Gemma · mradermacher
Params3.88B
Context128K
Q4_K_M2.5 GB
GGUF
HU
Huihui Hunyuan MT Chimera 7B Abliterated
Huihui · mradermacher
Params7.5B
Context256K
Q4_K_M4.6 GB
GGUF
CL
Claire 7B 0.1
Claire · mradermacher
Params7.22B
Context2K
Q4_K_M5.0 GB
GGUF
WI
WizardMath 7B V1.1 i1
Wizardmath · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
WI
WizardLM-2-8x22B
Wizardlm · backyardai
Params141B
Context64K
Q4_K_M85.6 GB
GGUF
DA
danube2-1.8b-Synthia-v1.3
Danube · mradermacher
Params1.83B
Context8K
Q4_K_M1.1 GB
GGUF
QW
Qwen3.5 40B Claude 4.6 Opus Deckard Heretic Uncensored Thinking
Qwen · mradermacher
Params39.1B
Context256K
Q4_K_M23.9 GB
CodingReasoningRoleplay
IC
Iced-Lemon-Cookie-7B
Iced · backyardai
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
QW
Qwen3 VL 2B Instruct Abliterated v1
Qwen · prithivMLmods
Params1.72B
Context256K
Q4_K_M1.1 GB
Vision
MI
Mirai 70B 0.1 Public Alpha
Mirai · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
Roleplay
MI
Ministral 3 8B Base 2512
Mistral · mradermacher
Params8.49B
Context256K
Q4_K_M5.2 GB
GGUF
IC
IceTea21EnergyDrinkRPV13 dpo240 i1
Icetea · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MI
Mistral v0.2 Nexus Internal Knowledge Map 7B i1
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
ST
Step 3.5 Flash REAP 149B A11B i1
Step · mradermacher
Params149B
Context256K
Q4_K_M89.9 GB
GGUF
ER
Erk 14B
Erk · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
GGUF
LL
Llama-3.1-Argunaut-1-8B-HIRPO
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
Reasoning
MI
Mistral Nemo Instruct 2407 abliterated i1
Mistral · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
ST
L3.1 Storniitova 8B i1
Storniitova · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
LL
dolphin 2.9.4 llama3.1 8b i1
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
Coding
QW
Qwen3 VL 8B NSFW Caption V4.5
Qwen · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
Vision
GP
Gpt Oss 20b RichardErkhov Heresy
gpt-oss · mradermacher
Params20.9B
Context128K
Q4_K_M15.8 GB
GGUF
LO
LongWriter V 7B
Longwriter · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
GGUF
PE
Pelican1.0 VL 235B A22B FC
Pelican · mradermacher
Params235B
Context256K
Q4_K_M142.2 GB
Vision
MI
MissLizzy_7b_HF
Misslizzy · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
QW
I2S Qwen3 8B Confidence
Qwen · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
CU
CursorCore QW2.5 7B i1
Cursorcore · mradermacher
Params7.61B
Context32K
Q4_K_M4.7 GB
Coding
QW
Qwen3.5 9B Polaris HighIQ THINKING
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningRoleplay
QW
Qwen2.5 1.5B Instruct Abliterated
Qwen · mradermacher
Params1.54B
Context32K
Q4_K_M1.0 GB
GGUF
DA
Darwin 35B A3B Opus
Darwin · bartowski
Params34.7B
Context256K
Q4_K_M21.4 GB
ReasoningTool useVision
LL
Phind CodeLlama 34B Python v1
Llama · mradermacher
Params33.7B
Context16K
Q4_K_M20.2 GB
Coding

Other quants

Keep browsing