Q4_K_S GGUF models

4-bit k-quant, small. Slightly smaller and a little lower quality than Q4_K_M. 104639 models have a Q4_K_S file. Sizes run from 1M to 1030B parameters. The longest trained context is 4194304K tokens.

Most downloadedNewestLargestLongest contextSmallest
OP
weyaxi_openchat-3.5-1210-seraph-slerp
Openchat · TheBloke
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
LL
Llama 3 Meerkat 8b v1.0
Llama · RichardErkhov
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
FR
Free_Sydney_13b_HF
Free · mradermacher
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
GE
Gemma 3 12b It Qat
Gemma · bartowski
Params11.8B
Context128K
Q4_K_M7.3 GB
Vision
QW
Qwen2.5 Coder 14B Instruct
Qwen · gaianet
Params14.8B
Context32K
Q4_K_M9.0 GB
Coding
LI
Lily-Cybersecurity-7B-v0.2
Lily · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
QW
QVQ 72B Preview
Qwen · bartowski
Params72.7B
Context125K
Q4_K_M47.4 GB
Vision
LL
Llama 3.1 Nemotron 70B Instruct HF
Llama · bartowski
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
AM
llm360_amberchat
Amberchat · TheBloke
Params6.74B
Context2K
Q4_K_M4.1 GB
GGUF
WI
ehartford_wizardlm-30b-uncensored
Wizardlm · TheBloke
Params32.5B
Context2K
Q4_K_M19.6 GB
GGUF
NE
NVIDIA Nemotron 3.5 Lightning 30B A3B
Nemotron · NANI-Nithin
Params32.9B
Context1024K
Q4_K_M25.4 GB
GGUF
LL
Llama3.1 Heretic Unsensored
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
CodingTool use
CY
Cydonia 24B v4.3 Heretic
Cydonia · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
Coding
HU
Huozi3.5
Huozi · mradermacher
Params46.9B
Context32K
Q4_K_M28.6 GB
GGUF
LL
CodeLlama 13b Hf
Llama · mradermacher
Params13B
Context16K
Q4_K_M7.9 GB
Coding
FR
FrogNano 4B 2609 Heretic
Frognano · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
GGUF
EX
Experiment26 7B
Experiment · MaziyarPanahi
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
NO
Noema 1.5 4B Deep
Noema · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
CodingReasoning
QW
Qwen3.5 4B Anon Reasoning v2
Qwen · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool use
OR
Ornith 1.0 35B Uncensored Heretic
Ornith · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
GGUF
VI
vicuna 13B v1.5
Vicuna · TheBloke
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
PY
Pythia 160m Deduped
Pythia · mradermacher
Params162M
Context2K
Q4_K_M0.1 GB
GGUF
SU
SummLlama3.1 8B
Summllama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
FU
Fugaku-LLM-13B-instruct
Fugaku · mmnga
Params13.4B
Context2K
Q4_K_M9.6 GB
GGUF
SY
migtissera_synthia-70b-v1.2
Synthia · TheBloke
Params69B
Context2K
Q4_K_M41.4 GB
GGUF
LL
Llama 3.2 1B Instruct Abliterated
Llama · mradermacher
Params1.5B
Context128K
Q4_K_M1.0 GB
GGUF
GE
Gemma 2 Ataraxy 9B
Gemma · bartowski
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
SK
Sky T1 32B Preview
Sky · bartowski
Params32.8B
Context32K
Q4_K_M19.9 GB
GGUF
FI
Fin R1
Fin · mradermacher
Params7.6B
Context32K
Q4_K_M4.7 GB
Reasoning
CA
camel-ai_camel-13b-role-playing-data
Camel · TheBloke
Params13B
Context2K
Q4_K_M7.9 GB
Roleplay

Other quants

Keep browsing