IQ3_XXS GGUF models
A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 28129 models have a IQ3_XXS file. Sizes run from 2M to 2450B parameters. The longest trained context is 10240K tokens.
CA
Captain Eris Diogenes Twilight V0.420 12B GGUF ARM Imatrix
Captain · Lewdiculous
Params12.2B
Context1000K
Q4_K_M7.5 GB
LL
Dobby Unhinged Llama 3.3 70B
Llama · bartowski
Params70.6B
Context128K
Q4_K_M42.5 GB
LE
Lexi Coder v5.1
Lexi · mradermacher
Params7.25B
Context32K
Q4_K_M4.4 GB
GE
Gemma 4 Gemsicle 31B
Gemma · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
LL
llama-3-tulu-2-8b
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
OL
Olmo 3 7B Instruct
OLMo · bartowski
Params7.3B
Context64K
Q4_K_M4.5 GB
GR
Granite 4.0 H Tiny
Granite · mradermacher
Params6.94B
Context1024K
Q4_K_M4.2 GB
WA
Wayfarer 2 12B Absolute Heresy
Wayfarer · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
GP
Gpt Oss 20b
gpt-oss · mradermacher
Params20.9B
Context128K
Q4_K_M15.8 GB
LL
Llama 3.2 1B Instruct
Llama · ThomasBaruzier
Params1.24B
Context128K
Q4_K_M0.8 GB
SM
Smart Commit 1.5b v0.3
Smart · mradermacher
Params1.54B
Context32K
Q4_K_M1.0 GB
KL
Klyrune 2B Coder
Klyrune · mradermacher
Params2.52B
Context128K
Q4_K_M1.6 GB
SI
SIREN 3B
Siren · mradermacher
Params3.09B
Context32K
Q4_K_M1.9 GB
RO
Roleplay 9B lora 800 porn i1
Roleplay · mradermacher
Params8.83B
Context16K
Q4_K_M5.3 GB
KI
Kiwen1.1 27B
Kiwen · bartowski
Params27.3B
Context256K
Q4_K_M17.8 GB
GE
Gemma 4 12B It Uncensored Opus4.7 Cot
Gemma · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
NE
Nemo Gutenberg 12b v1
Nemo · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
QW
Qwen3 Stargate SG1 Uncensored Abliterated 8B
Qwen · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
LL
Llama-3-Lumimaid-8B-v0.1-OAS
Llama · Lewdiculous
Params8B
Context8K
Q4_K_M4.9 GB
GE
BgGPT Gemma 2 9B IT v1.0
Gemma · mradermacher
Params9.24B
Context8K
Q4_K_M5.8 GB
ZE
zen 4b i1
Zen · mradermacher
Params4.02B
Context32K
Q4_K_M2.5 GB
QW
Qwen3.6 27B Omnimerge v4 MTP
Qwen · ManniX-ITA
Params27.3B
Context256K
Q4_K_M16.8 GB
RW
rwkv7 g1h 2.9b i1
Rwkv · RemySkye
Params2.95B
Context1024K
Q4_K_M2.1 GB
LL
Llama 3.1 8B UltraMedical
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
LF
Abliterated
Lfm · alexwkleung
Params24B
Context128K
Q4_K_M14.5 GB
OC
OceanGPT-7b-v0.1
Oceangpt · mradermacher
Params6.74B
Context2K
Q4_K_M4.1 GB
MO
Moe 4x7b reason code qa i1
Moe · mradermacher
Params24.2B
Context32K
Q4_K_M14.6 GB
LL
Llama 3 Youko 70b Instruct
Llama · mmnga
Params70.6B
Context8K
Q4_K_M42.5 GB
LF
LFM2.5 230M
Lfm · mradermacher
Params230M
Context125K
Q4_K_M0.2 GB
QW
WebWorld 14B
Qwen · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB