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 27B Uncensored Chinese
Qwen · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
GGUF
KE
Kev-9B Artemis 4.1GB
Kev · turintech
Params8.96B
Context256K
Best fitIQ3_M 6.4 GB
ReasoningTool use
JA
Jan-v1-4B
Jan · janhq
Params4B
Context256K
Best fitQ8_0 6.0 GB
GGUF
KA
Kainaticulous Rp 7b
Kainaticulous · mradermacher
Params7.24B
Context32K
Best fitQ6_K 7.5 GB
Roleplay
QW
Qwen3 8B JP Uncensored
Qwen · ryo559
Params8.19B
Context40K
Best fitQ8_0 10.4 GB
GGUF
GE
gemma-2-9b-it
Gemma · legraphista
Params9.24B
Context8K
Best fitQ6_K 10.9 GB
GGUF
GL
GLM 4.6V
GLM · mradermacher
Params107B
Context128K
Q4_K_M70.4 GB
GGUF
QW
Qwen3.5 abliterated MAX AIO
Qwen · prithivMLmods
Params752M
Context256K
Best fitQ8_0 10.4 GB
Vision
GR
Granite 3b Code Base 2k
Granite · mradermacher
Params3.48B
Context2K
Best fitQ6_K 6.0 GB
Coding
NY
Nyakura CausalLM RP 34B i1
Nyakura · mradermacher
Params34.4B
Context195K
Best fitIQ2_XXS 11.8 GB
Roleplay
QW
Qwen3.8 27B TQ
Qwen · YTan2000
Params27.3B
Context256K
Smallest0.8 GB
GGUF
LL
togethercomputer_llama-2-7b-32k-instruct
Llama · TheBloke
Params6.74B
Context32K
Best fitQ8_0 12.0 GB
GGUF
TA
UI TARS 7B DPO
Tars · bartowski
Params7.62B
Context32K
Best fitQ8_0 9.1 GB
Vision
MI
Mixtral_7Bx2_MoE_13B
Mistral · mradermacher
Params12.9B
Context32K
Best fitQ5_K_M 10.7 GB
GGUF
MI
Sydney_Pirate_Mistral_7b
Mistral · mradermacher
Params7.24B
Context32K
Best fitQ6_K 7.5 GB
GGUF
ME
q-bert_metamath-cybertron-starling
Metamath · TheBloke
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
GGUF
ST
StarCoder
StarCoder · mradermacher
Params15.5B
Context8K
Best fitQ5_K_S 11.6 GB
Coding
FL
Sakura FLUX.3 Image Klein PromptUpsampler Uncensored
Flux · webmp3
Params8.95B
Context256K
Best fitQ8_0 11.1 GB
Vision
HO
Holo4 35B A3B
Holo · mradermacher
Params34.7B
Context256K
Best fitIQ2_S 11.8 GB
GGUF
BO
Boulesis v2.1 26B A4B HeadTune
Boulesis · mradermacher
Params26B
Context256K
Q4_K_M17.2 GB
ReasoningRoleplayTool use
QW
Qwen3 4B toolcalling gguf codex
Qwen · Manojb
Params4B
Context256K
Smallest4.3 GB
CodingTool use
QW
Qwen3.5 4B
Qwen · dahara1
Params4.21B
Context256K
Best fitBF16 10.0 GB
ReasoningTool useVision
MI
ANITA NEXT 24B Dolphin Mistral UNCENSORED ITA
Mistral · mradermacher
Params23.6B
Context40K
Best fitIQ3_XS 11.7 GB
Reasoning
NE
NVIDIA Nemotron 3.5 Bolt E4B
Nemotron · bartowski
Params7.52B
Context64K
Best fitQ8_0 9.9 GB
ReasoningTool useVision
QW
Swift 1.5 Qwen3.8 27b Heretic
Qwen · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
Vision
DI
digital socrates 7b i1
Digital · mradermacher
Params6.74B
Context4K
Best fitQ6_K 10.3 GB
GGUF
GE
Mahou-1.3-gemma2-9B
Gemma · mradermacher
Params9.24B
Context8K
Best fitQ6_K 10.9 GB
GGUF
DE
MultiPL-T-DeepSeekCoder_33b
DeepSeek · mradermacher
Params33.3B
Context16K
Best fitIQ2_XXS 11.5 GB
Coding
AU
Aura Prototype 26B A4B
Aura · mradermacher
Params26B
Context256K
Q4_K_M17.2 GB
Roleplay
SM
SmolLM 135M
SmolLM · QuantFactory
Params135M
Context2K
Best fitQ2_K 0.8 GB
GGUF

Other memory sizes

Keep browsing