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.
LI
LightOnOCR 3 4B
Lightonocr · prithivMLmods
Params4.21B
Context256K
Best fitBF16 10.0 GB
HA
Harrier Oss v1 0.6b
Harrier · mradermacher
Params596M
Context32K
Best fitF16 2.6 GB
DE
decider 4b
Decider · Mapika
Params4.2B
Context256K
Best fitBF16 10.0 GB
QW
Qwen3.8 9B Distill Uncensored Heretic
Qwen · mradermacher
Params9.2B
Context256K
Best fitQ6_K 9.2 GB
QW
Huihui Qwen3 VL 8B Instruct Abliterated
Qwen · noctrex
Params8.19B
Context256K
Best fitQ8_0 10.4 GB
QW
Qwen3-Vl-2B-Thinking
Qwen · unsloth
Params1.72B
Context256K
Best fitBF16 4.9 GB
TR
Translategemma 4b It
Translategemma · SandLogicTechnologies
Params3.88B
Context128K
Best fitQ5_K_M 4.5 GB
RO
TheDrummer Rocinante XL 16B v1
Rocinante · bartowski
Params16.1B
Context128K
Best fitQ4_0 11.7 GB
QW
Qwen3.5 4B heretic imatrix
Qwen · FadedRedStar
Params334M
Context256K
Best fitQ5_K_M 4.6 GB
QW
Qwen3.8 27B abliterated MTP
Qwen · hotdogs
Params27B
Context256K
Q4_K_M16.8 GB
QW
Qwen2.5 VL 3B Instruct
Qwen · mradermacher
Params3.09B
Context125K
Best fitF16 7.0 GB
XX
encoder
Xxl · chatpig
Params219M
Context512
Best fitQ8_0 8.8 GB
OR
Ornith 1.5 9b Mtp
Ornith · protoLabsAI
Params456M
Context256K
Best fitQ8_0 11.4 GB
LY
Lythri 4B A2B
Lythri · bartowski
Params4.63B
Context128K
Best fitBF16 10.4 GB
NE
NeoHorse-1-4B
Neohorse · TokenRhythm
Params4.21B
Context256K
Best fitBF16 10.0 GB
DE
WhiteRabbitNeo WhiteRabbitNeo V3 7B
Deephat · bartowski
Params7.62B
Context32K
Best fitQ8_0 9.1 GB
LF
LiquidAI_LFM2.5 1.2B Instruct
Lfm · lmstudio-community
Params1.17B
Context125K
Best fitQ8_0 2.8 GB
QW
Qwen3 VL 8B Heretic Stable
Qwen · mradermacher
Params8.19B
Context256K
Best fitQ8_0 10.4 GB
LL
Llama 3.2 8X4B MOE V2 Dark Champion Instruct uncensored abliterated 21B
Llama · DavidAU
Params20.9B
Context128K
Best fitQ3_K_M 11.8 GB
GL
Glm-4-9B-0414
GLM · unsloth
Params9.4B
Context32K
Best fitQ8_0 10.8 GB
GR
Granite 20b Code Instruct
Granite · bartowski
Params20B
Context8K
Best fitIQ4_XS 11.7 GB
FO
Foundation Sec 8B Reasoning
Foundation · fdtn-ai
Params8B
Context128K
Best fitQ4_K_M 6.5 GB
HO
K2-Horizon-MoVA-36B-A4B
Horizon · mradermacher
Params37.4B
Context512K
Best fitIQ1_M 10.8 GB
QW
Qwen3 8B Heretic
Qwen · mradermacher
Params8.19B
Context40K
Best fitQ8_0 10.4 GB
QW
Qwen3.5 9B Coder
Qwen · mradermacher
Params9.2B
Context256K
Best fitQ8_0 11.4 GB
MI
Mistral Small 3.1 24B Instruct 2503
Mistral · bartowski
Params23.6B
Context128K
Best fitIQ3_XS 11.7 GB
MI
MiniCPM5 2B Math
MiniCPM · Caldalis
Params2.52B
Context128K
Best fitBF16 5.9 GB
MI
Ministral-3-14B-Reasoning-2512
Mistral · unsloth
Params13.5B
Context256K
Best fitQ5_K_M 11.5 GB
NE
NVIDIA Nemotron 3.5 Bolt E4B Uncensored
Nemotron · AtomicChat
Params7.5B
Context64K
Best fitQ6_K 9.3 GB
MA
UI Mate 9B
Mate · bartowski
Params8.95B
Context256K
Best fitQ8_0 11.1 GB