IQ2_XS GGUF models
A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 26336 models have a IQ2_XS file. Sizes run from 2M to 2450B parameters. The longest trained context is 10240K tokens.
ST
MN 12B Starcannon v3 i1
Starcannon · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
LL
Meta Llama 3.1 70B
Llama · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
TO
Tower Plus 9B Abliterated Hf Data
Tower · mradermacher
Params9.24B
Context8K
Q4_K_M5.8 GB
LL
Llm Jp 3 8x1.8b Instruct3
Llm · mmnga
Params9.27B
Context4K
Q4_K_M5.7 GB
LL
Meta-Llama-3-70B-Instruct
Llama · mradermacher
Params70.6B
Context8K
Q4_K_M42.5 GB
QW
Qwen3 30B A3B Instruct 2507 FT
Qwen · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
LL
Llama 3.1 Nemotron 70B Instruct HF abliterated
Llama · bartowski
Params70.6B
Context128K
Q4_K_M42.5 GB
OH
Ohm MythosHeretic
Ohm · mradermacher
Params3.09B
Context128K
Q4_K_M1.9 GB
MA
MagnumChronos i1
Magnumchronos · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
HY
HyperLLama3.1 8b Nova i1
Hyperllama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
LL
Infinity Instruct 7M 0729 Llama3_1 70B
Llama · mradermacher
Params70.6B
Context8K
Q4_K_M42.5 GB
DE
deepseek-coder-6.7b-instruct
DeepSeek · duyntnet
Params6.74B
Context16K
Q4_K_M4.1 GB
QW
Qwen3.8 27B Uncensored Heretic v3
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
MI
Karen_TheEditor_V2_STRICT_Mistral_7B
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
LL
Code-Llama-3-8B
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
FA
Fara TARS 7B
Fara · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
QW
Qwen2.5 14B
Qwen · mradermacher
Params14.8B
Context128K
Q4_K_M9.0 GB
QW
UniReason Qwen3 14B No Think SFT
Qwen · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
OR
Ornith 1.5 35B A3B 3MPER0RR Abliterated
Ornith · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
BA
Baichuan M2 32B
Baichuan · bartowski
Params32.8B
Context128K
Q4_K_M19.9 GB
BA
Bagel Dpo 8x7b v0.2
Bagel · bartowski
Params46.7B
Context32K
Q4_K_M28.4 GB
HU
Hunyuan A13B Instruct
Hunyuan · bartowski
Params80.4B
Context256K
Q4_K_M49.3 GB
LL
Llama 3.1 8B Instruct Abliterated Obliteratus
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
QW
Huihui Qwen3 Coder Next Opus 4.6 Reasoning Distilled abliterated
Qwen · Momix-44
Params80B
Context256K
Q4_K_M48.5 GB
PO
Poro 34B chat i1
Poro · mradermacher
Params35.1B
Context7K
Q4_K_M22.4 GB
RO
Rocinante 12B v1.1 i1
Rocinante · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
MO
MotherEarth Hermes 8B i1
Motherearth · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
SU
SuperNova Medius
Supernova · arcee-ai
Params14.8B
Context128K
Q4_K_M9.0 GB
GE
Gemma 3 12b It Ultra Heretic
Gemma · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
XW
XwinCoder 7B i1
Xwincoder · mradermacher
Params6.74B
Context16K
Q4_K_M4.1 GB