IQ3_XS GGUF models
A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 46199 models have a IQ3_XS file. Sizes run from 1M to 1030B parameters. The longest trained context is 102400K tokens.
QW
Qwen3.5 27B RpRMax v1
Qwen · bartowski
Params27B
Context256K
Q4_K_M17.5 GB
OM
Omni R1
Omni · mradermacher
Params7B
Context5K
Q4_K_M4.3 GB
MI
K2S3 Mistral 7b v1.46
Mistral · RichardErkhov
Params7.37B
Context32K
Q4_K_M4.5 GB
CH
ChemLLM 20B Chat DPO
Chemllm · mradermacher
Params19.9B
Context32K
Q4_K_M12.0 GB
IN
Internlm2_5 20b Chat
InternLM · bartowski
Params19.9B
Context32K
Q4_K_M12.0 GB
DA
danube2-1.8b-Tess-v1.5
Danube · mradermacher
Params1.83B
Context8K
Q4_K_M1.1 GB
MI
Mistral Claude merged
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.5 GB
QW
Qwen2.5 Coder 1.5B Unsensored DPO
Qwen · mradermacher
Params1.54B
Context32K
Q4_K_M1.0 GB
GE
gemma 2 2b rebus solver fp16
Gemma · mradermacher
Params2.61B
Context8K
Q4_K_M1.7 GB
AI
airoboros-2.2.1-limarpv3-y34b
Airoboros · mradermacher
Params34.4B
Context4K
Q4_K_M20.7 GB
YI
Yi-9B-Coder
Yi · mradermacher
Params8.83B
Context4K
Q4_K_M5.3 GB
QW
Qwen3 4B Instruct 2507 Abliterated
Qwen · mradermacher
Params4B
Context256K
Q4_K_M2.5 GB
GE
Huihui Gemma 4 12B It Abliterated
Gemma · mradermacher
Params11.9B
Context128K
Q4_K_M7.4 GB
AT
Athene 70B
Athene · mradermacher
Params70.6B
Context8K
Q4_K_M42.5 GB
MI
mistral 7b orpo v5.0
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
PH
Phi 3 song lyrics 1.0 i1
Phi · mradermacher
Params3.82B
Context4K
Q4_K_M2.4 GB
DA
datagemma rig 27b it
Datagemma · bartowski
Params27.2B
Context8K
Q4_K_M16.6 GB
ME
mera mix 4x7B i1
Mera · mradermacher
Params24.2B
Context32K
Q4_K_M14.6 GB
AR
Arcee Nova
Arcee · arcee-ai
Params72.7B
Context32K
Q4_K_M47.4 GB
GP
Gpt Oss 20b Uncensored Heretic
gpt-oss · mradermacher
Params20.9B
Context128K
Q4_K_M15.8 GB
SW
Swallow-7b-plus-hf
Swallow · mradermacher
Params6.83B
Context4K
Q4_K_M4.1 GB
PR
ProgressGym-HistLlama3-70B-C013-instruct-v0.1
Progressgym · mradermacher
Params70.6B
Context8K
Q4_K_M42.5 GB
QW
Josiefied Qwen3 8B Abliterated v1
Qwen · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
SA
Saltware-solar-10.7b-v1.0
Saltware · mradermacher
Params10.7B
Context4K
Q4_K_M6.5 GB
CO
Yi Coder 1.5B Chat
Coder · mradermacher
Params1.48B
Context128K
Q4_K_M1.0 GB
LL
Llama 3.2 8X3B GATED MOE Horror Reasoning Dark Champion uncensored 18.4B IMAT
Llama · DavidAU
Params18.4B
Context128K
Q4_K_M11.8 GB
LI
limstral 7B v0.1
Limstral · mradermacher
Params7.24B
Context32K
Q4_K_M4.5 GB
LL
Llama-3-70b-Uncensored-Lumi-Tess-gradient
Llama · mradermacher
Params70.6B
Context256K
Q4_K_M42.5 GB
IN
L3.1 Instruct Guru 8B
Instruct · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
QW
Qwen3.5 35B A3B Claude 4.6 Opus Reasoning Distilled
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB