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 30B A3B Gemini Pro High Reasoning 2507 ABLITERATED UNCENSORED
Qwen · mradermacher
Params30.5B
Context256K
Best fitQ2_K_S 11.8 GB
Reasoning
ST
stable-code-instruct-3b
Stable · mradermacher
Params2.8B
Context16K
Best fitQ6_K 5.5 GB
Coding
MI
Mistral7B-PairRM-SPPO
Mistral · mradermacher
Params7.24B
Context32K
Best fitQ6_K 7.5 GB
GGUF
FR
FrogNano 4B 2609 GGUF jang imatrix
Frognano · roman220220
Params4.33B
Context256K
Smallest0.6 GB
Vision
MI
norquinal_mistral-7b-claude-chat
Mistral · TheBloke
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
GGUF
MI
Nous-Hermes-2-Mixtral-8x7B-DPO
Mistral · mradermacher
Params46.7B
Context32K
Best fitIQ1_S 11.4 GB
Tool use
QW
Qwen3.5 4B Abliterated
Qwen · mradermacher
Params4.21B
Context256K
Best fitF16 10.0 GB
GGUF
KN
KnowLine 4B Gen5.5
Knowline · mradermacher
Params4.33B
Context256K
Best fitF16 10.3 GB
ReasoningTool useVision
MA
Mage VL
Mage · JohnTdi
Params21M
Context256K
Best fitQ8_0 6.4 GB
Vision
AS
astrollama 2 7b chat aic i1
Astrollama · mradermacher
Params6.74B
Context4K
Best fitQ6_K 10.3 GB
GGUF
OP
openchat_openchat_3.5
Openchat · TheBloke
Params7.24B
Context8K
Best fitQ8_0 9.3 GB
GGUF
LL
Llama3.2 30B A3B II Dark Champion INSTRUCT Heretic Abliterated Uncensored
Llama · mradermacher
Params30B
Context128K
Best fitIQ2_S 11.3 GB
Roleplay
QW
Qwen2.5.1 Coder 1.5B Instruct
Qwen · bartowski
Params1.54B
Context32K
Best fitF16 3.8 GB
Coding
PH
Tess v2.5 Phi 3 medium 128k 14B i1
Phi · mradermacher
Params14B
Context128K
Best fitQ5_K_S 11.8 GB
GGUF
GL
GLM-4.7-Flash-Coder
GLM · ngquocvinh
Params30B
Context198K
Best fitIQ2_XS 10.2 GB
Coding
GL
GLM 4.5V
GLM · mradermacher
Params107B
Context64K
Q4_K_M70.4 GB
GGUF
LL
Llama 3.1 1 million cxt Dark Planet 8B
Llama · DavidAU
Params8B
Context1048K
Best fitQ8_0 10.1 GB
Roleplay
QW
Qwen3.6 35B A3B DFlash
Qwen · magnitudedev
Params386M
Context40K
Best fitQ8_0 1.1 GB
GGUF
MI
MiniCPM5 2B Claude Fable5 heretic
MiniCPM · saidutta69
Params2.52B
Context128K
Best fitF16 5.9 GB
ReasoningTool use
TE
Ingot XVI 27B Q2
Ternary · dendriteholdings
Params26.9B
Context256K
Smallest5.9 GB
ReasoningTool use
QW
Qwen3 TTS 12Hz 0.6B Base
Qwen · mradermacher
Params600M
Context32K
Best fitF16 2.7 GB
Vision
MI
Mistral dolphin mix cine open Ne NSFW
Mistral · mradermacher
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
GGUF
QW
Qwen3.8 2B
Qwen · piskle
Params1.94B
Context256K
Best fitBF16 4.8 GB
GGUF
SW
Swallow-7b-hf
Swallow · mradermacher
Params6.83B
Context4K
Best fitQ6_K 10.4 GB
GGUF
QW
Qwythos 9B v2
Qwythos · bartowski
Params9.2B
Context1024K
Best fitQ8_0 11.4 GB
Reasoning
MI
Hermes 2 Pro Mistral 7B
Mistral · backyardai
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
Tool use
LI
H2O Lightning 4b
Lightning · mradermacher
Params4.21B
Context256K
Best fitF16 10.0 GB
GGUF
CA
CAJAL 4B Merged 16bit
Cajal · Agnuxo
Params4.21B
Context256K
Best fitF16 10.0 GB
GGUF
QW
Qwen3.5 0.8B Japanese SFT v2
Qwen · mradermacher
Params752M
Context256K
Best fitQ5_K_S 1.5 GB
GGUF
QW
Qwen2.5 Coder 3B Uncensored
Qwen · bappi
Params3.1B
Context32K
Best fitQ8_0 4.1 GB
Coding

Other memory sizes

Keep browsing