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.
YI
Hermes-2.5-Yi-1.5-9B-Chat
Yi · mradermacher
Params8.83B
Context4K
Best fitQ6_K 8.6 GB
QW
dolphin-2.9.2-qwen2-7b
Qwen · dphn
Params7.62B
Context128K
Best fitQ8_0 9.1 GB
GE
Gemma 3 270m It
Gemma · bartowski
Params268M
Context32K
Best fitBF16 1.2 GB
GE
Gemory 26B A4B SOMPOA
Gemory · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
SP
SpydazWebAI_Human_AGI
Spydazwebai · mradermacher
Params7.24B
Context512K
Best fitQ6_K 7.5 GB
QW
Qwythos 9B v2
Qwythos · mradermacher
Params9.2B
Context1024K
Best fitQ8_0 11.4 GB
QW
Qwen3 VL 8B Abliterated Caption It
Qwen · mradermacher
Params8.19B
Context256K
Best fitQ8_0 10.4 GB
GE
gemma 4 e2b yemeni arabic assistant
Gemma · yemeni-ai-lab
Params4.63B
Context128K
Best fitBF16 10.4 GB
AH
Ahma 7B
Ahma · mradermacher
Params7B
Context2K
Best fitQ6_K 10.5 GB
SH
Shadow Siren 26B A4B
Shadow · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
MI
Infinity Instruct 7M 0729 Mistral 7B
Mistral · mradermacher
Params7.24B
Context32K
Best fitQ6_K 7.5 GB
GE
Google_Gemma 4 E4B It Qat Q4_0 Unquantized
Gemma · lmstudio-community
Params7.46B
Context128K
Best fitQ4_0 7.1 GB
SO
SOLAR 10.7B Instruct v1.0
Solar · TheBloke
Params10.7B
Context4K
Best fitQ6_K 10.9 GB
GR
granite-3b-code-base
Granite · mradermacher
Params3.48B
Context2K
Best fitQ6_K 6.0 GB
CA
CantoneseLLM v2.0 8B Thinking Chat Vector Merged
Cantonesellm · mradermacher
Params8.19B
Context40K
Best fitQ6_K 8.4 GB
QW
Qwen3.6 35B A3B REAP 48 v2
Qwen · crucible-labs
Params19.2B
Context256K
Smallest9.4 GB
OR
Ornith 1.5 REAP 20B A3B
Ornith · sleepyeldrazi
Params19B
Context256K
Best fitIQ4_NL 11.7 GB
IN
Index Nailong 9B
Index · mradermacher
Params8.95B
Context224K
Best fitQ6_K 8.9 GB
MA
mamba 130m hf
Mamba · QuantFactory
Params129M
Context1024K
Best fitQ8_0 0.7 GB
HY
HybridAgent 14B Agentic
Hybridagent · bartowski
Params14.8B
Context32K
Best fitQ4_K_L 11.9 GB
VI
T VisStar 7B v0.1 i1
Visstar · mradermacher
Params7.29B
Context32K
Best fitQ6_K 7.6 GB
QW
Qwen3.8 27B Escha W2
Qwen · aj9o9
Params6.33B
Context256K
Best fitF16 5.6 GB
MI
Mistral-11B-SynthIAirOmniMix
Mistral · mradermacher
Params10.7B
Context32K
Best fitQ6_K 10.9 GB
VI
Vietnamese 4B Chat abliterated
Vietnamese · N14QM
Params4.2B
Context256K
Best fitF16 10.0 GB
GE
Gemma 2B Uncensored
Gemma · lemuralabs
Params2.51B
Context8K
Best fitF16 5.7 GB
KI
Kiwen1.1 27B
Kiwen · NikiKrutan
Params27.3B
Context256K
Best fitIQ2_S 11.6 GB
QW
Huihui Qwen3.5 9B Claude 4.6 Opus Abliterated Heretic
Qwen · mradermacher
Params8.95B
Context256K
Best fitQ6_K 8.9 GB
LL
Hermes 2 Theta Llama 3 8B
Llama · NousResearch
Params8B
Context8K
Best fitQ8_0 10.1 GB
QW
Qwen2.5 7B Instruct abliterated v2
Qwen · kepom
Params7.6B
Context32K
Best fitQ8_0 9.1 GB
QW
Qwen3.5 2B EmperoAI Qwen3.8 Distill Heretic Abliterated
Qwen · mradermacher
Params1.88B
Context256K
Best fitF16 4.7 GB