GGUF models that fit in 32 GB

198257 GGUF language models have at least one quant whose estimated memory use is 32 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
MI
Ministral 3 14B Instruct 2512
Mistral · bartowski
Params13.5B
Context256K
Best fitBF16 28.9 GB
Vision
PH
dolphin-2.9.2-Phi-3-Medium
Phi · legraphista
Params14B
Context4K
Best fitBF16 30.1 GB
CodingTool use
GR
Granite-4.0-350M
Granite · unsloth
Params352M
Context32K
Best fitBF16 2.1 GB
GGUF
LI
Ling 3.0 Flash
Ling · bartowski
Params127B
Context256K
Q4_K_M77.8 GB
GGUF
NA
Nanbeige4.2 3B
Nanbeige · owao
Params4.17B
Context256K
Best fitQ8_0 5.7 GB
GGUF
WI
Wicked Stuff 26B A4B Final
Wicked · mradermacher
Params25.2B
Context256K
Best fitQ6_K 31.2 GB
ReasoningTool use
QW
Qwen3.6 27B Uncensored Heretic v2
Qwen · llmfan46
Params27B
Context256K
Best fitQ8_0 31.2 GB
Vision
GL
GLM 4.5 Air Derestricted
GLM · bartowski
Params110B
Context128K
Q4_K_M73.5 GB
GGUF
QW
Qwen2.5 Coder 3B Instruct
Qwen · lmstudio-community
Params3.09B
Context32K
Best fitQ8_0 4.1 GB
Coding
QW
Bonsai 2 27B 1bit CRACK
Qwen · dealignai
Params27B
Context256K
Smallest5.9 GB
GGUF
QW
Qwen3.5-9B
Qwen · jc-builds
Params8.95B
Context256K
Best fitQ4_K_M 7.3 GB
Reasoning
QW
Qwen2.5 Coder 32B Instruct
Qwen · CISCai
Params32.8B
Context32K
Best fitIQ4_XS 20.3 GB
Coding
DA
L3 DARKEST PLANET 16.5B
Darkest · DavidAU
Params16.5B
Context8K
Best fitQ8_0 21.4 GB
Roleplay
QW
Qwen3.8 27B Optimal Ablit Heretic
Qwen · mradermacher
Params27B
Context256K
Best fitQ6_K 24.8 GB
GGUF
EU
EuroLLM 1.7B Instruct
Eurollm · mradermacher
Params1.66B
Context8K
Best fitF16 4.6 GB
GGUF
QW
Qwen2.5 VL 32B Instruct
Qwen · bartowski
Params32.8B
Context125K
Best fitQ6_K_L 29.9 GB
Vision
QW
Qwen3.6 14B A3B VibeForged v2
Qwen · tvall43
Params13.8B
Context256K
Best fitQ8_0 15.8 GB
Vision
ME
Medgemma 27b It
Medgemma · bartowski
Params27B
Context128K
Best fitQ6_K_L 27.2 GB
EmbeddingVision
QW
Qwen3 30B A3B Thinking 2507
Qwen · bartowski
Params30.5B
Context256K
Best fitQ6_K_L 26.6 GB
Reasoning
QW
Qwen3.8 27B
Qwen · Jackrong
Params461M
Context256K
Best fitQ8_0 31.7 GB
Vision
QW
Qwen3 4b Heretic
Qwen · DreamFast
Params11.8B
Context40K
Best fitF16 25.2 GB
Coding
FA
Fara1.5 27B
Fara · bartowski
Params27B
Context256K
Best fitQ8_0 31.3 GB
Vision
GU
GUI Owl 1.5 8B Instruct
Gui · mradermacher
Params8.19B
Context32K
Best fitF16 18.1 GB
Vision
QW
Huihui Qwen3.5 27B Abliterated
Qwen · mradermacher
Params27B
Context256K
Best fitQ6_K 24.7 GB
GGUF
VI
Vikhr Nemo 12B Instruct R 21 09 24 Q4 K M
Vikhr · VlSav
Params12.2B
Context1000K
Best fitQ4_K_M 9.3 GB
GGUF
SW
Swish 26B A4B Final
Swish · mradermacher
Params25.2B
Context256K
Best fitQ6_K 31.2 GB
ReasoningRoleplayTool use
GP
Gpt Oss 20b Heretic
gpt-oss · bartowski
Params20.9B
Context128K
Best fitQ6_K 23.1 GB
GGUF
QW
Qwen3.8 27B Antislop
Qwen · mradermacher
Params27B
Context256K
Best fitQ6_K 24.7 GB
GGUF
QW
Qwen3.8 27B TWIN TURBO Fable Cold Fusion 709 L Uncensored NVFP4
Qwen · esatapedico
Params27.3B
Context256K
Smallest14.9 GB
GGUF
QW
Qwen3.8-Flash-Next
Qwen · ji-farthing
Params177B
Context256K
Smallest2.4 GB
GGUF

Other memory sizes

Keep browsing