Q4_K_L GGUF models

A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 1891 models have a Q4_K_L file. Sizes run from 30M to 1030B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
HA
Hathor_Gamma-L3-8B-0.6
Hathor · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
FI
Fireball 12B v1.0
Fireball · bartowski
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
LL
Llama 3.2 1B Instruct
Llama · weluvmusic767-maker
Params1.24B
Context128K
Q4_K_M0.8 GB
Tool use
TE
Tempmotacilla Cinerea 0302
Tempmotacilla · bartowski
Params14.8B
Context128K
Q4_K_M9.0 GB
Tool use
BU
Buddy 2B v1
Buddy · bartowski
Params2.61B
Context8K
Q4_K_M1.7 GB
GGUF
GE
gemma 4 A4B 98e v7 coderx it
Gemma · fribourgquant
Params19.9B
Context256K
Q4_K_M13.2 GB
CodingReasoningTool use
MA
Maginum Cydoms 24B
Maginum · Casual-Autopsy
Params23.6B
Context128K
Q4_K_M14.3 GB
ReasoningRoleplay
QW
Qwen3.6 27B uncensored heretic v2
Qwen · Jolex98
Params26.9B
Context256K
Smallest10.2 GB
ReasoningRoleplayTool use
PH
Phi Line_14B
Phi · bartowski
Params14.7B
Context16K
Q4_K_M8.9 GB
GGUF
PH
Phi 3.5 Mini Instruct
Phi · stratalab-org
Params3.82B
Context128K
Q4_K_M2.4 GB
Coding
MI
Voxtral Small 24B 2507
Mistral · kukidevalml
Params23.6B
Context128K
Q4_K_M14.3 GB
Tool useVision
GE
gemma 4 19B A4B text REAP
Gemma · potto007
Params19.5B
Context256K
Q4_K_M13.0 GB
ReasoningTool use
LL
Llama 3.2 3B Instruct
Llama · EasierAI
Params3.61B
Context128K
Q4_K_M2.2 GB
Tool use
SU
MS Sunfall v0.7.0
Sunfall · bartowski
Params22.2B
Context32K
Q4_K_M13.3 GB
RoleplayTool use
QW
Qwen2.5 Math 7B Instruct
Qwen · chiakelvin
Params7.62B
Context4K
Q4_K_M4.7 GB
Tool use
HU
Hunyuan 1.8B Instruct
Hunyuan · Dzluck
Params1.79B
Context256K
Q4_K_M1.1 GB
ReasoningTool use
DE
Qwen2.5 32B
DeepSeek · viwo50
Params32.8B
Context128K
Q4_K_M19.9 GB
ReasoningTool use
MI
Mini Magnum 12b v1.1
Mini · Reiterate3680
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
LL
Llama 3.2 1B Instruct
Llama · AlexRudy
Params1.24B
Context128K
Q4_K_M0.8 GB
Tool use
GE
Gemma 2 2b Jpn It
Gemma · dahara1
Params2.61B
Context8K
Q4_K_M1.7 GB
GGUF
AR
Arcee-Spark
Arcee · arcee-ai
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
QW
Qwen3.5 9B Qworus V2
Qwen · DarkKitsune
Params8.95B
Context256K
Smallest0.0 GB
GGUF
LL
L3-Zodiac-8B-ORPO-Base
Llama · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
QW
Qwen3.5-35B-A3B
Qwen · hossamdaoud
Params34.7B
Context256K
Q4_K_M19.9 GB
ReasoningTool useVision
QW
Qwen2.5.1 Coder 7B Instruct
Qwen · sagemax
Params7.62B
Context32K
Q4_K_M4.7 GB
CodingTool use
IC
IceAbsintheRP 7b imat GGUFs
Iceabsintherp · Casual-Autopsy
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
LL
Llama-3SOME-8B-v2
Llama · bartowski
Params8.03B
Context10K
Q4_K_M4.9 GB
GGUF
YI
Fook-Yi-34B-32K-v1
Yi · bartowski
Params34.4B
Context32K
Q4_K_M20.7 GB
GGUF
QW
Qwen3.6 27B Omnimerge v4 MTP
Qwen · shaffhausen
Params27.3B
Context256K
Q4_K_M16.8 GB
ReasoningTool useVision
QW
QwenPaw Flash 9B Heretic
Qwen · daydreamwarrior
Params8.95B
Context256K
Smallest5.9 GB
CodingReasoningTool use

Other quants

Keep browsing