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.
LL
llava 1.6
LLaVA · cmp-nct
Params7.24B
Context32K
Best fitQ5_K 10.8 GB
OL
OLMoE 1B 7B 0125 Instruct
OLMo · allenai
Params6.9B
Context4K
Best fitQ8_0 8.9 GB
FA
Falcon3 10B Instruct
Falcon · bartowski
Params10.3B
Context32K
Best fitQ6_K_L 10.5 GB
SM
SmolLM2 135M Instruct
SmolLM · lmstudio-community
Params135M
Context8K
Best fitQ3_K_L 0.8 GB
RY
RynnUnify Agentic Reasoner
Rynnunify · mradermacher
Params8.19B
Context256K
Best fitQ6_K 8.4 GB
MI
jphme_em_german_leo_mistral
Mistral · TheBloke
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
QW
ComfyUI Qwen3 VL
Qwen · Abiray
Params8.77B
Context256K
Best fitQ5_K_M 8.6 GB
OP
openchat_openchat-3.5-0106
Openchat · TheBloke
Params7.24B
Context8K
Best fitQ8_0 9.3 GB
MU
Muse Glimmer 30B pruned V2.5 en pl
Muse · bluevoid-pl
Params27B
Context128K
Best fitIQ3_XXS 11.6 GB
MI
chronos mistral 7b i1
Mistral · mradermacher
Params7.24B
Context8K
Best fitQ6_K 7.5 GB
MI
models--bullerwins--Codestral-22B-v0.1-hf
Mistral · MaziyarPanahi
Params22.2B
Context32K
Best fitQ3_K_S 12.0 GB
DE
DeepSeek R1 Distill Qwen 14B 3MPER0RR Abliterated
DeepSeek · mradermacher
Params14.8B
Context128K
Best fitQ4_1 11.5 GB
QW
Qwen3 8B ERP v0.1
Qwen · Aratako
Params8.19B
Context40K
Best fitQ8_0 10.4 GB
OP
openPangu 2.0 Flash
Openpangu · mrexodia
Params91.6B
Context512K
Best fitQ8_0 10.5 GB
JA
AI21 Jamba Reasoning 3B
Jamba · bartowski
Params3.2B
Context256K
Best fitBF16 9.3 GB
SA
Salience 27B R5
Salience · bartowski
Params27.3B
Context1024K
Q4_K_M17.8 GB
NE
NeuralMona MoE 4x7B i1
Neuralmona · mradermacher
Params24.2B
Context32K
Best fitIQ3_XS 11.6 GB
KA
KAI 7B Instruct v0.1
Kai · mradermacher
Params7.24B
Context32K
Best fitQ6_K 7.5 GB
TE
Ternary Bonsai 2 27B Abliterated swift cap PQ2 0 MTP
Ternary · hotdogs
Params27.3B
Context256K
Smallest7.6 GB
VE
Veritas 8B Fact Checker Non Thinking 1.0
Veritas · mradermacher
Params8.19B
Context40K
Best fitQ6_K 8.4 GB
LL
model
Llama · ChatGpt1
Params8B
Context8K
Best fitQ8_0 10.1 GB
QW
Qwen2.5 Coder 7B Instruct
Qwen · CISCai
Params7.62B
Context32K
Best fitIQ4_XS 5.2 GB
HU
HumanlikeRP
Humanlikerp · mradermacher
Params8.83B
Context12K
Best fitQ6_K 8.6 GB
BE
Behemoth X 123B v2.2
Behemoth · bartowski
Params123B
Context128K
Q4_K_M76.3 GB
MI
Trinity 2 Codestral 22B v0.2
Mistral · bartowski
Params22.2B
Context32K
Best fitQ3_K_S 12.0 GB
QW
Qwen3.5 4B EmperoAI Qwen3.8 Distill Heretic Abliterated
Qwen · mradermacher
Params4.21B
Context256K
Best fitQ6_K 5.0 GB
MI
paixai_astrid-mistral-7b
Mistral · TheBloke
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
LL
LlamaScientific 8B
Llama · mradermacher
Params8.03B
Context128K
Best fitQ6_K 8.2 GB
RO
rocket 3B
Rocket · TheBloke
Params2.8B
Context4K
Best fitQ8_0 6.2 GB
JI
Jina Reranker v3.5
Jina · jinaai
Params596M
Context128K
Best fitBF16 2.6 GB