Q2_K GGUF models

2-bit k-quant. Smallest files and a clear drop in quality. Use it only when memory is very tight. 112215 models have a Q2_K file. Sizes run from 1M to 2780B parameters. The longest trained context is 4194304K tokens.

Most downloadedNewestLargestLongest contextSmallest
LL
Llama 3_1 Nemotron 51B Instruct
Llama · bartowski
Params51.5B
Context128K
Q4_K_M31.0 GB
GGUF
MI
Solstice Mixtral v1 i1
Mistral · mradermacher
Params46.7B
Context32K
Q4_K_M28.6 GB
GGUF
GE
Gemma 4 26B A4B It SOMPOA Heresy
Gemma · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
GGUF
MI
OpenHermes-2.5-Mistral-7B-x2
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Tool use
MI
MiniCPM V 2 6
MiniCPM · bartowski
Params7.6B
Context32K
Q4_K_M4.7 GB
CodingVision
QW
Qwen3-14B-128K
Qwen · unsloth
Params14.8B
Context128K
Q4_K_M9.0 GB
GGUF
QW
Qwythos 9B v2
Qwythos · mradermacher
Params9.2B
Context1024K
Q4_K_M5.8 GB
Reasoning
QW
Dongfangshuo Qwen3.8 27B NSFW
Qwen · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
RoleplayVision
SK
Skyfall 31B v4.2 Heretic
Skyfall · mradermacher
Params31.4B
Context128K
Q4_K_M19.0 GB
Coding
MI
severian_anima-phi-neptune-mistral-7b
Mistral · TheBloke
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
GR
Granite Guardian 4.1 8b
Granite · ibm-granite
Params8.38B
Context128K
Q4_K_M5.1 GB
ReasoningTool use
QW
PopiT Qwen3 4B Medical SFT 1128
Qwen · mradermacher
Params4B
Context40K
Q4_K_M2.5 GB
GGUF
NE
NeoHorse 1 9 Uncensored
Neohorse · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool use
EK
Ekbasis 27B
Ekbasis · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
GGUF
UN
ajibawa-2023_uncensored-jordan-7b
Uncensored · TheBloke
Params6.74B
Context2K
Q4_K_M4.1 GB
GGUF
KA
KansenSakura Eclipse RP 12b
Kansensakura · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
Roleplay
OP
openbuddy-yi1.5-34b-v21.3-32k
Openbuddy · mradermacher
Params34.4B
Context128K
Q4_K_M20.7 GB
GGUF
LL
Llama 3.2 3B Instruct
Llama · mradermacher
Params3.61B
Context128K
Q4_K_M2.2 GB
GGUF
GE
Gemma 4 12B It Heretic_Decensored
Gemma · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
Vision
GL
Huihui GLM 4.6V Flash abliterated
GLM · AliBilge
Params9.4B
Context128K
Q4_K_M6.2 GB
Vision
MI
MiniCPM V 4.7 1B Heretic
MiniCPM · mradermacher
Params1.01B
Context256K
Q4_K_M0.7 GB
RoleplayVision
QW
Qwen3-Vl-8B-Thinking-1M
Qwen · unsloth
Params8.19B
Context977K
Q4_K_M5.0 GB
ReasoningVision
GR
Granite 8b Code Instruct 4k
Granite · RichardErkhov
Params8.05B
Context4K
Q4_K_M4.9 GB
Coding
DE
DeepSeek V2.5
DeepSeek · bartowski
Params236B
Context160K
Q4_K_M142.5 GB
GGUF
HY
HyperNova 60B
Hypernova · mradermacher
Params58.7B
Context128K
Q4_K_M40.7 GB
Tool use
QW
WhereOPD Qwen3.5 4B
Qwen · mradermacher
Params4.84B
Context256K
Q4_K_M3.1 GB
GGUF
LL
Llama-3-Instruct-Neurona-8b-v2
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
CodingTool use
LF
LFM2.5 24B A2B Abliterated
Lfm · mradermacher
Params24B
Context128K
Q4_K_M14.5 GB
ReasoningTool use
OP
openthaigpt 1.0.0 beta 13B chat
Openthaigpt · TheBloke
Params13.1B
Context4K
Q4_K_M7.9 GB
GGUF
LL
CodeUp Llama 2 13B Chat HF
Llama · TheBloke
Params13B
Context4K
Q4_K_M7.9 GB
Coding

Other quants

Keep browsing