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.
OR
Ornith 1.5 27B A3B CoderX MTP
Ornith · ManniX-ITA
Params26.2B
Context256K
Best fitQ2_K_L 11.5 GB
MI
Mistral Nemo 12B ArliAI RPMax v1.3
Mistral · ArliAI
Params12.2B
Context128K
Best fitQ6_K 11.9 GB
MI
Mistral 7B Instruct v0.2
Mistral · RichardErkhov
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
JI
jina embeddings v2 base code
Jina · second-state
Params160M
Context8K
Best fitF16 1.1 GB
TO
tokyotech llm Swallow 13b instruct v0.1
Tokyotech · mmnga
Params13.1B
Context4K
Best fitIQ2_M 11.8 GB
LL
Hermes 3 Llama 3.1 8B
Llama · legraphista
Params8B
Context128K
Best fitQ8_0 10.1 GB
SW
Swallow-7b-instruct-v0.1
Swallow · mradermacher
Params6.83B
Context4K
Best fitQ6_K 10.4 GB
QW
Qwen2.5 Coder 7B Instruct Heretic
Qwen · saidutta69
Params7.62B
Context32K
Best fitQ8_0 9.1 GB
KI
Huihui Kimi Linear 48B A3B Instruct Abliterated
Kimi · mradermacher
Params49.1B
Context1024K
Q4_K_M29.7 GB
LL
Hermes 3 Llama 3.1 8B
Llama · mradermacher
Params8B
Context128K
Best fitQ6_K 8.2 GB
GE
Gemma 3 4b It
Gemma · DavidAU
Params3.88B
Context128K
Best fitQ8_0 6.4 GB
TI
Tiny Aya Global
Tiny · CohereLabs
Params3.35B
Context488K
Best fitBF16 7.8 GB
HO
K2 Horizon 7B
Horizon · NANI-Nithin
Params9B
Context512K
Best fitQ8_0 11.3 GB
OX
OxCoder 9B GMCE
Oxcoder · mradermacher
Params8.95B
Context256K
Best fitQ6_K 8.9 GB
UM
umiyuki Japanese Chat Umievo itr001 7b
Umiyuki · mmnga
Params7.24B
Context4K
Best fitQ8_0 9.3 GB
YI
dolphin-2.9.1-yi-1.5-34b
Yi · mradermacher
Params34.4B
Context8K
Best fitIQ2_XXS 11.8 GB
GE
Gemmasutra Mini 2B v1
Gemma · l3utterfly
Params2.61B
Context8K
Best fitF16 6.6 GB
ME
Melody1437 35B A3B
Melody · ReadyArt
Params35.5B
Context256K
Q4_K_M21.7 GB
QW
Qwen2.5 Coder 32B Instruct Uncensored i1
Qwen · mradermacher
Params32.8B
Context32K
Best fitIQ2_XXS 11.7 GB
DE
DeepSeek R1 Distill Qwen 1.5B Abliterated
DeepSeek · mradermacher
Params1.78B
Context128K
Best fitF16 4.3 GB
GR
Granite 7b Base
Granite · mradermacher
Params6.74B
Context4K
Best fitQ6_K 10.3 GB
EX
models--automerger--Experiment28Experiment29-7B
Experiment · MaziyarPanahi
Params7.24B
Context32K
Best fitQ6_K 7.5 GB
LI
T Lite It 1.0
Lite · aovchinnikov
Params7.6B
Context32K
Best fitQ4_K_M 5.7 GB
LL
Llama3.2 DeepHermes 3 3B Preview Reasoning MAX NEO Imatrix
Llama · DavidAU
Params3.21B
Context128K
Best fitF16 7.9 GB
GR
Granite Speech 5.0 2b
Granite · ibm-granite
Params1.84B
Context16K
Best fitBF16 4.8 GB
IC
IceTea21EnergyDrinkRPV13 DPOv3 i1
Icetea · mradermacher
Params7.24B
Context32K
Best fitQ6_K 7.5 GB
LL
gguf lora llama3 midjourney prompt generator
Llama · rvian
Params8B
Context8K
Best fitQ4_K_M 6.5 GB
RU
RusMind.Вспышка 3.5
Rusmind · DICPlay
Params7.52B
Context128K
Best fitQ8_0 9.9 GB
QW
ThinkingCap Qwen3.6 27B
Qwen · bartowski
Params27.3B
Context256K
Q4_K_M17.8 GB
CO
ConfigurableSOLAR 10.7B i1
Configurablesolar · mradermacher
Params10.7B
Context4K
Best fitQ6_K 10.9 GB