Q5_K_L GGUF models

A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 1644 models have a Q5_K_L file. Sizes run from 30M to 403B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
LL
Llama-3-Perky-Pat-Instruct-8B
Llama · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
QW
QwQ 32B Preview abliterated
Qwen · Iambackup
Params32B
Context—
Q4_K_M19.9 GB
Reasoning
LL
Halu 8B Llama3 Blackroot
Llama · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
AR
Arcee Maestro 7B Preview
Arcee · arcee-ai
Params7.61B
Context128K
Q4_K_M4.7 GB
ReasoningTool use
QW
Qwen2.5 32B AGI
Qwen · williamchangtw
Params32.8B
Context32K
Q4_K_M19.9 GB
GGUF
FA
Fara 7B
Fara · AlexKitipov
Params7.62B
Context125K
Q4_K_M4.7 GB
Vision
MI
Dolphin Mistral 24B Venice Edition
Mistral · Yixman
Params23.6B
Context32K
Q4_K_M14.3 GB
GGUF
QW
Qwen2.5 3B Instruct
Qwen · dahara1
Params3.09B
Context32K
Q4_K_M1.9 GB
Tool use
QW
Virtuoso Small
Qwen · arcee-ai
Params14.8B
Context128K
Q4_K_M9.0 GB
Tool use
LL
llama-3-meerkat-8b-v1.0
Llama · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
QW
Qwen2.5 Coder 14B Instruct Abliterated
Qwen · Juju-sxkxi
Params14.8B
Context32K
Q4_K_M9.0 GB
CodingTool use
QW
Qwen2.5 Coder 14B Instruct Abliterated
Qwen · colton6901
Params14.8B
Context32K
Q4_K_M9.0 GB
CodingTool use
TU
Tunguska 39B V1A Workspace
Tunguska · bartowski
Params39B
Context128K
Q4_K_M23.4 GB
Tool use
LL
dolphin 2.9 llama3 8b
Llama · kafirind17
Params8.03B
Context8K
Q4_K_M4.9 GB
CodingTool use
OV
OvisOCR2
Ovisocr · manojbillionaire123
Params752M
Context256K
Q4_K_M0.6 GB
ReasoningTool useVision
HA
Hathor_Stable-L3-8B-v0.5
Hathor · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
ME
MetaStone L1 7B
Metastone · bartowski
Params7.62B
Context128K
Q4_K_M4.7 GB
ReasoningTool use
GE
Gemma 3 27b It Abliterated
Gemma · danielmnd
Params27B
Context128K
Q4_K_M16.5 GB
Vision
QW
Qwen2.5 1.5B Instruct
Qwen · dahara1
Params1.54B
Context32K
Q4_K_M1.0 GB
Tool use
QW
Qwen2.5 14B Instruct
Qwen · dahara1
Params14.8B
Context32K
Q4_K_M9.0 GB
Tool use
LL
New-Dawn-Llama-3-70B-32K-v1.0
Llama · bartowski
Params70.6B
Context32K
Q4_K_M42.5 GB
GGUF
AR
arcee lite
Arcee · bartowski
Params1.78B
Context32K
Q4_K_M1.1 GB
GGUF
RE
Retrograde Omega M 22B v1.0
Retrograde · bartowski
Params22.2B
Context128K
Q4_K_M13.3 GB
Tool use
PH
gguf sharded Phi 3 mini 4k instruct
Phi · Felladrin
Params3.82B
Context4K
Q4_K_M2.4 GB
GGUF
GE
Replete LLM gemma 9b test merged 250k
Gemma · bartowski
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
LL
llama3-turbcat-instruct-8b
Llama · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
BL
.\BlackSheep
Blacksheep · bartowski
Params3.82B
Context8K
Q4_K_M2.3 GB
GGUF
AP
rootxhacker Apollo v3 32B
Apollo · bartowski
Params32.8B
Context32K
Q4_K_M19.9 GB
Tool use
LL
Hercules 6.1 Llama 3.1 8B
Llama · bartowski
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
HE
Hermes 4 14B
Hermes · genevaquant
Params14.8B
Context40K
Q4_K_M9.0 GB
ReasoningTool use

Other quants

Keep browsing