Q2_K_L GGUF models

A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 2217 models have a Q2_K_L file. Sizes run from 80M to 1030B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
HA
Hathor_Respawn-L3-8B-v0.8
Hathor · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
Llama 3 8B Stroganoff 3.0
Llama · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
QW
QwQ 32B Preview
Qwen · divpasta123
Params32.8B
Context32K
Q4_K_M19.9 GB
ReasoningTool use
DR
Dracarys2 72B Instruct
Dracarys · bartowski
Params72.7B
Context32K
Q4_K_M47.4 GB
Tool use
QW
Huihui Qwen3.8 27B Abliterated
Qwen · xleeelx
Params27.3B
Context256K
Smallest10.9 GB
ReasoningTool useVision
SM
Smegmma-Deluxe-9B-v1
Smegmma · bartowski
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
GE
Gemma4 RustyBender
Gemma · nathanles
Params11.9B
Context256K
Q4_K_M7.4 GB
ReasoningTool useVision
DI
.\DigitalSoul
Digitalsoul · bartowski
Params4.62B
Context128K
Q4_K_M2.9 GB
Tool use
QW
Huihui Qwen3.8 27B Abliterated
Qwen · Ivanuk4PDA
Params27.3B
Context256K
Smallest10.9 GB
ReasoningTool useVision
LL
Llama-4-Scout-17B-16E-Instruct
Llama · jburmeister
Params108B
Context10240K
Q4_K_M65.4 GB
Tool useVision
QW
Qwen3.5 2B Medical Reasoning
Qwen · xtools-at
Params1.88B
Context256K
Q4_K_M1.3 GB
ReasoningTool useVision
AR
arcee lite
Arcee · arcee-ai
Params1.78B
Context32K
Q4_K_M1.1 GB
GGUF
QW
Qwen3.5 4BxOpus 4.6 Code Reasoning Full Distilled
Qwen · nphearum
Params4.21B
Context256K
Q4_K_M2.7 GB
CodingReasoningTool use
GE
Gemma 4 31B It
Gemma · shainmeena
Params30.7B
Context256K
Q4_K_M19.6 GB
ReasoningTool useVision
QW
Qwen3-Vl-30B-A3B-Instruct
Qwen · tripolskypetr
Params30.5B
Context256K
Q4_K_M18.6 GB
Tool useVision
IN
QuixiAI Ina v11.1
Ina · bartowski
Params70.6B
Context128K
Q4_K_M42.5 GB
RoleplayTool use
QW
Qwen3-4B-Instruct-2507
Qwen · cmp-nct
Params4.02B
Context256K
Q4_K_M2.5 GB
ReasoningTool use
LL
Apollo 0.4 Llama 3.1 8B
Llama · bartowski
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
MO
Moxin Chat
Moxin · bartowski
Params8.11B
Context32K
Q4_K_M4.9 GB
GGUF
TW
TwinLlama 3.1 8B trl
Twinllama · bartowski
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
LL
Apollo 2.0 Llama 3.1 8B
Llama · bartowski
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
MI
MindLink 72B 0801
Mindlink · bartowski
Params72.7B
Context32K
Q4_K_M47.4 GB
Tool use
OP
OpenCrystal 12B L3
Opencrystal · bartowski
Params11.5B
Context8K
Q4_K_M7.0 GB
GGUF
EV
L3-8B-Everything-COT
Everything · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
GE
godot gemma 4 e2b it
Gemma · bekoozkan
Params4.65B
Context128K
Q4_K_M3.4 GB
ReasoningTool useVision
GE
genmyanmar 3 E4B it
Gemma · BaybeDragon
Params6.87B
Context32K
Q4_K_M4.5 GB
Vision
LL
Llama 3.2 3B Instruct
Llama · Jadzblaze99
Params3.61B
Context128K
Q4_K_M2.2 GB
Tool use
LL
Llama 3.3 70B Instruct Abliterated
Llama · Justbackup
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use
QW
Qwen2.5 Coder 14B Instruct Abliterated
Qwen · td-builder
Params14.8B
Context32K
Q4_K_M9.0 GB
CodingTool use
HA
Hathor_Aleph-L3-8B-v0.72
Hathor · bartowski
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF

Other quants

Keep browsing