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.
QW
Qwen3 4B RPG Roleplay V2
Qwen · Chun121
Params4B
Context32K
Best fitF16 9.8 GB
BI
bitnet b1.58 2B 4T
Bitnet · microsoft
Params2.41B
Context4K
Smallest1.2 GB
QW
Qwen3.8 Flash Next Uncensored
Qwen · AtomicChat
Params80M
Context256K
Q4_K_M93.9 GB
TI
TinyMistral 248M v2 Instruct
Tinymistral · M4-ai
Params248M
Context32K
Best fitQ8_0 0.9 GB
QW
Qwen3.8 27B Unleashed
Qwen · outsourc-e
Params27B
Context256K
Best fitIQ2_S 11.1 GB
DA
DanTagGen delta rev2
Dantaggen · KBlueLeaf
Params393M
Context2K
Best fitF16 2.1 GB
LA
Laya
Laya · ggml-org
Params421M
Context8K
Best fitBF16 2.4 GB
QW
XORTRON RICO v3
Qwen · darkc0de
Params27.3B
Context256K
Q4_K_M16.8 GB
SP
Spark X2.6 4B Abliterated
Spark · SC117
Params4.11B
Context1024K
Best fitBF16 9.9 GB
QW
Qwen3 0.6b Abliterated
Qwen · mradermacher
Params596M
Context40K
Best fitQ5_K_S 1.9 GB
GL
Models Zai Org GLM 4.6V Flash
GLM · MaziyarPanahi
Params9.4B
Context128K
Best fitQ6_K 9.1 GB
MI
MiniCPM-V-4.7-35B-A3B
MiniCPM · AtomicChat
Params34.7B
Context256K
Best fitIQ2_XXS 11.3 GB
MI
mistralai_Ministral 3 3B Instruct 2512 BF16
Mistral · lmstudio-community
Params3.43B
Context256K
Best fitQ8_0 5.0 GB
NE
NeoHorse 1 4B
Neohorse · mradermacher
Params4.21B
Context256K
Best fitQ6_K 5.0 GB
MU
Muse Glimmer 30B
Muse · bartowski
Params27.9B
Context128K
Best fitQ2_K 12.0 GB
GL
cerebras/GLM-4.7-Flash-REAP-23B-A3B
GLM · unsloth
Params23B
Context198K
Best fitQ3_K_S 11.6 GB
OR
Ornith 1.5 9B Heretic v2
Ornith · Thunder13240
Params8.95B
Context256K
Best fitQ8_0 11.1 GB
JI
JiRackUltra 1b
Jirackultra · CMSManhattan
Params1.78B
Context128K
Q4_K_M1.1 GB
NA
Nanbeige4.3 33B UNCENSORED
Nanbeige · dealignai
Params33.1B
Context512K
Best fitIQ2_XXS 11.6 GB
MI
Devstral Small 2 24B Instruct 2512
Mistral · bartowski
Params23.6B
Context384K
Best fitIQ3_XS 11.7 GB
QW
Qwen3 VL 2B Instruct
Qwen · ggml-org
Params1.72B
Context256K
Best fitQ8_0 3.3 GB
LL
codellama_codellama-7b-instruct-hf
Llama · TheBloke
Params6.74B
Context16K
Best fitQ8_0 12.0 GB
MI
MistralRP Noromaid NSFW Mistral 7B
Mistral · Ttimofeyka
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
QW
Qwen3.8 27B Uncensored
Qwen · BnhHo
Params27.3B
Context256K
Best fitQ8_0 5.8 GB
QW
Qwen3.8-27B-DFlash2
Qwen · incoai
Params1.92B
Context256K
Best fitBF16 4.5 GB
QW
Huihui Qwen3 VL 8B Instruct Abliterated
Qwen · mradermacher
Params8.19B
Context256K
Best fitQ8_0 10.4 GB
BG
bge m3 Q8 0
BGE · ggml-org
Params567M
Context8K
Best fitQ8_0 1.9 GB
NE
NVIDIA Nemotron Nano 9B v2
Nemotron · bartowski
Params8.89B
Context1024K
Q4_K_M6.5 GB
QW
Qwen3-Vl-30B-A3B-Instruct
Qwen · unsloth
Params30.5B
Context256K
Best fitIQ2_XXS 11.6 GB
TE
HY MT1.5 7B
Tencent · tencent
Params7.5B
Context256K
Best fitQ8_0 9.6 GB