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
Qwen2.5 14B
Qwen · bartowski
Params14.8B
Context128K
Best fitQ4_K_L 11.7 GB
Roleplay
QW
Qwen3 14B
Qwen · mradermacher
Params14.8B
Context40K
Best fitQ4_1 11.2 GB
ReasoningTool use
DO
Dolphin X1 8B
Dolphin · dphn
Params8B
Context128K
Best fitQ8_0 10.1 GB
GGUF
QW
Qwen3.8 27B Uncensored JoyFox Aggressive
Qwen · joyfox
Params27.3B
Context256K
Best fitBF16 8.6 GB
Vision
GL
AutoGLM Phone 9B
GLM · Luckybalabala
Params9.4B
Context64K
Best fitQ8_0 10.8 GB
Vision
BO
Bonsai 27b 1bit CRACK
Bonsai · dealignai
Params27B
Context256K
Best fitQ1_0 7.3 GB
ReasoningTool useVision
MA
Magnum 12b v2
Magnum · bartowski
Params12.2B
Context1000K
Best fitQ6_K 11.9 GB
GGUF
DA
DataPilot ArrowPro 7B KUJIRA
Datapilot · mmnga
Params7.24B
Context4K
Best fitQ8_0 9.3 GB
GGUF
MI
mistralai_Ministral 3 14B Instruct 2512 BF16
Mistral · lmstudio-community
Params13.5B
Context256K
Best fitQ4_K_M 10.1 GB
Vision
ST
L3-8B-Stheno-v3.3-32K
Stheno · DavidAU
Params8B
Context32K
Best fitQ8_0 10.1 GB
Roleplay
CO
Cosmos Reason2 2b
Cosmos · apolo13x
Params2.03B
Context256K
Best fitF16 5.5 GB
ReasoningVision
ST
Starling-LM-7B-alpha-x2
Starling · mradermacher
Params7.24B
Context8K
Best fitQ6_K 7.5 GB
GGUF
CO
C4Ai Command R7B 12 2024
Command R · bartowski
Params8B
Context8K
Best fitQ8_0 10.1 GB
GGUF
MI
E5 Mistral 7B Instruct Embedding
Mistral · second-state
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
Embedding
GR
Granite 4.0 H Tiny
Granite · bartowski
Params6.94B
Context1024K
Best fitQ8_0 9.9 GB
GGUF
QW
Qwen2.5 7B Instruct Heretic
Qwen · saidutta69
Params7.62B
Context32K
Best fitQ8_0 9.1 GB
Tool use
PY
Pythia 1b
Pythia · mradermacher
Params1.01B
Context2K
Best fitQ6_K 2.4 GB
GGUF
LL
dolphin 2.9 llama3 8b
Llama · QuantFactory
Params8B
Context8K
Best fitQ8_0 10.1 GB
CodingTool use
PR
Privacy Filter
Privacy · LocalAI-io
Params1.4B
Context128K
Best fitF16 3.4 GB
GGUF
GE
Gemma-4-E4B-It
Gemma · ente-ai
Params7.5B
Context128K
Best fitQ8_K_XL 10.6 GB
Vision
AS
AstaBrief_8B
Astabrief · mradermacher
Params8.2B
Context40K
Best fitQ6_K 8.4 GB
GGUF
MI
MiniCPM5 2B DSpark
MiniCPM · openbmb
Params324M
Context128K
Smallest0.7 GB
CodingTool use
QW
Qwen3.6 35B A3B Uncensored Heretic Native MTP Preserved
Qwen · mradermacher
Params35.5B
Context256K
Q4_K_M21.7 GB
GGUF
SP
Spark X2.6 4B Uncensored GSQ RCO
Spark · abenzerps
Params4.11B
Context1024K
Best fitIQ4_XS 4.3 GB
ReasoningTool use
RE
ReflectionCoder-CL-34B
Reflectioncoder · mradermacher
Params33.7B
Context16K
Best fitIQ2_XXS 11.1 GB
Coding
QW
Qwen3.8 4B Heretic
Qwen · mradermacher
Params4.21B
Context256K
Best fitQ6_K 5.0 GB
GGUF
GE
Gemma 4 E4B It Ultra Uncensored Heretic
Gemma · mradermacher
Params7.52B
Context128K
Best fitQ8_0 9.9 GB
ReasoningTool useVision
MI
Mistral Nemo Instruct Heretic
Mistral · saidutta69
Params12.2B
Context128K
Best fitQ6_K 11.9 GB
RoleplayTool use
GR
granite 20b functioncalling i1
Granite · mradermacher
Params20B
Context8K
Best fitIQ4_XS 11.7 GB
GGUF
PY
Pythia 410m Deduped
Pythia · mradermacher
Params405M
Context2K
Best fitQ4_0 1.6 GB
GGUF

Other memory sizes

Keep browsing