GGUF models that fit in 12 GB

171517 GGUF language models have at least one quant whose estimated memory use is 12 GB or less at 8K context. Each card shows the largest quant that fits. Sizes run from 1M to 20260731B parameters. The longest trained context is 4194304K tokens.

Most downloadedNewestLargestLongest contextSmallest
CY
Cydonia 24B v4.1
Cydonia · bartowski
Params23.6B
Context128K
Best fitIQ3_XS 11.7 GB
GGUF
NO
argilla_notus-7b-v1
Notus · TheBloke
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
GGUF
CH
Chronos Gold 12B 1.0 i1
Chronos · mradermacher
Params12.2B
Context1000K
Best fitQ6_K 11.9 GB
Roleplay
MI
Ministral 3 3B Reasoning 2512
Mistral · bartowski
Params3.43B
Context256K
Best fitBF16 8.2 GB
ReasoningVision
OR
Ornith 1.0 9B MTP
Ornith · protoLabsAI
Params9.2B
Context256K
Best fitQ8_0 11.4 GB
GGUF
KO
Kohlibri 40B
Kohlibri · mradermacher
Params40.3B
Context256K
Best fitIQ1_M 10.6 GB
ReasoningTool use
MI
dolphin 2.2.1 mistral 7b i1
Mistral · mradermacher
Params7.24B
Context32K
Best fitQ6_K 7.5 GB
GGUF
QW
Qwen3.8-27B
Qwen · Hirt556
Params27.3B
Context256K
Best fitIQ2_S 11.5 GB
Vision
SK
Skyfall 31B v4.2 Abliterix
Skyfall · mradermacher
Params31.4B
Context128K
Best fitIQ2_XS 11.8 GB
GGUF
MI
Dolphin Mistral GLM 4.7 Flash 24B Venice Edition Thinking Uncensored
Mistral · mradermacher
Params23.6B
Context32K
Best fitIQ3_XS 11.7 GB
ReasoningRoleplay
LL
Hermes 3 Llama 3.2 3B
Llama · mradermacher
Params3.21B
Context128K
Best fitF16 7.9 GB
RoleplayTool use
CO
ConfigurableBeagle 11B i1
Configurablebeagle · mradermacher
Params10.7B
Context32K
Best fitQ6_K 10.9 GB
GGUF
ME
Meltemi 7B v1.5
Meltemi · mradermacher
Params7.48B
Context32K
Best fitQ6_K 7.7 GB
GGUF
SA
Sailor2 8B Chat
Sailor · bartowski
Params8.55B
Context32K
Best fitQ8_0 10.1 GB
GGUF
KU
sanjiwatsuki_kunoichi-7b
Kunoichi · TheBloke
Params7.24B
Context8K
Best fitQ8_0 9.3 GB
GGUF
MA
magnum v3 9b chatml
Magnum · bartowski
Params9.24B
Context8K
Best fitQ6_K_L 11.1 GB
GGUF
QW
Qwen3 Coder 30B A3B Instruct Heretic
Qwen · mradermacher
Params30.5B
Context256K
Best fitQ2_K_S 11.8 GB
Coding
GE
Gemma 4 E2B It Ultra Uncensored Heretic
Gemma · mradermacher
Params4.65B
Context128K
Best fitF16 10.4 GB
Vision
MI
Mistral Small 3.1 24B Instruct 2503 MAX NEO Imatrix
Mistral · DavidAU
Params23.6B
Context128K
Best fitIQ2_XS 11.1 GB
GGUF
PH
Phonellm Mini Alpha 2
Phonellm · mradermacher
Params31.6B
Context1024K
Q4_K_M24.5 GB
Tool use
RO
RoLlama3-8b-Instruct
Rollama · legraphista
Params8B
Context8K
Best fitQ8_0 10.1 GB
GGUF
WI
Wicked Stuff 26B A4B v3.0 Final
Wicked · bartowski
Params25.2B
Context256K
Q4_K_M18.0 GB
ReasoningRoleplayTool use
SW
Swish 26B A4B Final
Swish · ReadyArt
Params25.2B
Context256K
Q4_K_M16.8 GB
ReasoningRoleplayTool use
CO
ConfigurableHermes 7B i1
Configurablehermes · mradermacher
Params7.24B
Context32K
Best fitQ6_K 7.5 GB
Tool use
OR
Ornith 1.5 9B uncensored
Ornith · ressl
Params9.2B
Context256K
Best fitQ8_0 11.4 GB
Vision
ST
StartLux Decision v1 0.8B Q8 0
Startlux · startlux-models
Params752M
Context256K
Best fitQ8_0 1.7 GB
GGUF
QW
Qwen3.5 2B Claude 4.6 OS Auto Variable HERETIC UNCENSORED THINKING
Qwen · mradermacher
Params1.88B
Context256K
Best fitF16 4.7 GB
ReasoningRoleplayVision
GE
Gemma 2 2b It
Gemma · lmstudio-community
Params2.61B
Context8K
Best fitF32 11.8 GB
GGUF
ME
Mellum2 12B A2.5B Instruct
Mellum · bartowski
Params12.1B
Context128K
Best fitQ6_K 12.0 GB
GGUF
MI
Mistral Medium 3.5 128B Eschaton Uncensored
Mistral · mradermacher
Params125B
Context256K
Q4_K_M74.9 GB
Reasoning

Other memory sizes

Keep browsing