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.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen3.8 Flash Next
Qwen · bartowski
Params177B
Context256K
Best fitBF16 9.1 GB
Vision
MI
MiniCPM o 4 5
MiniCPM · openbmb
Params8.2B
Context40K
Best fitQ8_0 10.4 GB
Vision
QW
Qwen3.8 27B Uncensored
Qwen · orcarouter
Params27.3B
Context256K
Best fitIQ2_XXS 10.5 GB
ReasoningTool useVision
GE
Gemma 4 26B A4B It Ultra Uncensored Heretic
Gemma · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
GGUF
GE
gemma 2b
Gemma · google
Params2.51B
Context—
Smallest10.0 GB
GGUF
CP
CPH Community 7B
Cph · CypherTroopers
Params7B
Context—
Best fitQ4_K_M 0.5 GB
GGUF
QW
Qwen3.8 35B A3B Distill
Qwen · IsValorum
Params34.7B
Context256K
Best fitQ8_0 3.2 GB
ReasoningTool useVision
UN
Underdog Saluki 27B 1.0 MTP Abliterated
Underdog · Kujira
Params27.3B
Context256K
Smallest8.3 GB
Tool use
QW
Swift 1.5 Qwen3.8 27B Uncensored Dynamic MTP
Qwen · ajgazin
Params28B
Context256K
Best fitIQ2_XS 11.5 GB
Vision
MI
Cydonia 24B v4.3
Mistral · TheDrummer
Params23.6B
Context128K
Best fitQ2_K 10.7 GB
GGUF
GE
Gemma 4 E4B It Ultra Uncensored Heretic
Gemma · llmfan46
Params7.5B
Context128K
Best fitQ8_0 9.9 GB
Vision
GE
Gemma 3 1b It
Gemma · lmstudio-community
Params1B
Context32K
Best fitQ8_0 1.8 GB
GGUF
BO
Bonsai-1.7B
Bonsai · prism-ml
Params1.72B
Context32K
Best fitQ1_0 1.7 GB
GGUF
PA
PaddleOCR VL 1.6
Paddleocr · PaddlePaddle
Params467M
Context128K
Smallest0.9 GB
Vision
QW
Qwen3 4B Instruct 2507
Qwen · lmstudio-community
Params4B
Context256K
Best fitQ8_0 6.0 GB
GGUF
QW
Qwen3-Vl-2B-Instruct
Qwen · unsloth
Params1.72B
Context256K
Best fitBF16 4.9 GB
Vision
QW
Qwen2.5 Coder 3B Instruct AWQ
Qwen · Qwen
Params3.4B
Context32K
Q4_K_M2.1 GB
Coding
QW
Qwen3.8 27B Humanlike Chat
Qwen · LessThanThreeAI
Params26.9B
Context256K
Best fitF16 7.3 GB
ReasoningRoleplayTool use
GE
Gemma-3-270M-It
Gemma · unsloth
Params268M
Context32K
Best fitF16 1.2 GB
GGUF
GE
Gemma-4-E2B-Uncensored-HauhauCS-Aggressive
Gemma · HauhauCS
Params4.65B
Context128K
Best fitQ8_K 6.1 GB
Vision
ME
Mellum2 12B A2.5B Instruct
Mellum · JetBrains
Params12.1B
Context128K
Best fitQ4_K_M 9.0 GB
GGUF
QW
Qwen2.5 Omni 3B
Qwen · ggml-org
Params3.4B
Context32K
Best fitF16 7.6 GB
Vision
QW
Qwen3.6-27B
Qwen · ggml-org
Params26.9B
Context256K
Best fitBF16 8.6 GB
Vision
QW
Huihui Qwen3 Coder 30B A3B Instruct Abliterated
Qwen · mradermacher
Params30.5B
Context256K
Best fitQ2_K_S 11.8 GB
Coding
HE
Hermes 4 14B
Hermes · bartowski
Params14.8B
Context40K
Best fitQ4_K_L 11.4 GB
Tool use
MI
Devstral-Small-2-24B-Instruct-2512
Mistral · unsloth
Params23.6B
Context384K
Best fitIQ3_XXS 11.3 GB
CodingVision
QW
Qwen3.5-9B
Qwen · unsloth
Params9.2B
Context256K
Best fitQ8_0 11.4 GB
Vision
BT
BTL 4 Compact
Btl · badtheorylabs
Params34.7B
Context256K
Best fitIQ2_XXS 11.1 GB
Tool use
NE
Nemotron 3 Embed 1B Q4 K M
Nemotron · zenmagnets
Params1.14B
Context256K
Best fitQ4_K_M 1.8 GB
Embedding
GE
Gemma 3 4b It
Gemma · ggml-org
Params3.88B
Context128K
Best fitF16 9.4 GB
Vision

Other memory sizes

Keep browsing