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.
TE
Ternary Bonsai 2 27B DFlash2
Ternary · ProCreations
Params1.92B
Context256K
Best fitQ8_0 2.7 GB
OX
OxCoder 9B
Oxcoder · prithivMLmods
Params8.95B
Context256K
Best fitQ5_K_M 8.0 GB
QW
Greko 1.7b Beta Merged
Qwen · geolazagr
Params1.72B
Context40K
Best fitIQ4_NL 2.5 GB
GR
granite-8b-code-instruct
Granite · mradermacher
Params8.05B
Context4K
Best fitQ6_K 8.3 GB
GE
Gemmasutra Small 4B v1
Gemma · TheDrummer
Params3.86B
Context8K
Best fitQ8_0 6.0 GB
SU
Sugoi 14B Ultra
Sugoi · sugoitoolkit
Params14.8B
Context32K
Best fitQ4_K_M 11.1 GB
GE
Gemma 4 E4B it Artemis
Gemma · turintech
Params7.46B
Context128K
Best fitQ4_0 4.8 GB
QW
Qwen2.5 VL 7B Instruct
Qwen · DhruvalLabs
Params7.62B
Context125K
Best fitQ8_0 9.1 GB
YI
Yi-1.5-9B-Chat
Yi · bartowski
Params8.83B
Context4K
Best fitQ8_0 10.7 GB
QW
Qwen3-8B-128K
Qwen · unsloth
Params8.19B
Context128K
Best fitQ8_0 10.4 GB
OR
Ornith1.0 9B 3MPER0RR Abliterated
Ornith · mradermacher
Params8.95B
Context256K
Best fitQ6_K 9.0 GB
GL
GLM Z1 32B 0414
GLM · bartowski
Params32.6B
Context32K
Best fitIQ2_S 11.4 GB
QW
Qwen3 VL Reranker 2B
Qwen · mradermacher
Params1.72B
Context256K
Best fitQ6_K 2.9 GB
QW
Qwen3.8 9b Hermes Function Calling v2
Qwen · mradermacher
Params9.2B
Context256K
Best fitQ8_0 11.4 GB
QW
Qwen3.8 Flash Next
Qwen · TonyMFJ
Params51.2B
Context256K
Best fitQ4_K_M 4.1 GB
MI
Mistral-Large-4-1T-A52B-DSpark
Mistral · unsloth
Params1050B
Context1024K
Best fitBF16 4.8 GB
MI
Codestral 22B v0.1 IMat
Mistral · legraphista
Params22.2B
Context32K
Best fitQ3_K_S 12.0 GB
QW
Qwen3.5 122B A10B Heretic
Qwen · mradermacher
Params122B
Context256K
Q4_K_M74.2 GB
QW
Sperma Aj Qwen3.8 27b
Qwen · mradermacher
Params27B
Context256K
Best fitIQ2_S 12.0 GB
SK
Sketch Cydonia 24B V1.3
Sketch · mradermacher
Params23.6B
Context128K
Best fitIQ3_XS 11.7 GB
OL
Olmo-3-7B-Think
OLMo · unsloth
Params7.3B
Context64K
Best fitQ6_K_XL 11.6 GB
JI
jina embeddings v4 text retrieval
Jina · jinaai
Params3.1B
Context125K
Best fitF16 7.0 GB
MU
Muse Glimmer 30B
Muse · AaryanK
Params28B
Context128K
Best fitQ8_0 3.7 GB
SL
Slimaki Tavern 24B v1.3
Slimaki · mradermacher
Params23.6B
Context128K
Best fitIQ3_XS 11.7 GB
GL
Glm 4 9b Chat
GLM · bartowski
Params9.4B
Context128K
Best fitQ8_0 10.8 GB
LL
Llm Jp 4.1 8b Thinking
Llm · llm-jp
Params8.59B
Context64K
Best fitQ4_K_M 7.1 GB
QW
Qwen3 gabliterated image generation
Qwen · goonsai-com
Params4B
Context256K
Best fitQ8_0 6.0 GB
GR
Granite-4.1-8B
Granite · unsloth
Params8.79B
Context128K
Best fitQ8_0 11.2 GB
TO
Tongyi DeepResearch 30B A3B
Tongyi · bartowski
Params30.5B
Context128K
Best fitIQ2_M 11.2 GB
QW
Qwen3.8-27B
Qwen · haybar4k
Params27.3B
Context256K
Best fitIQ2_S 11.9 GB