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
NE
nexus legal
Nexus · King3Djbl
Params1.54B
Context32K
Best fitF16 3.8 GB
GGUF
ST
Stellar Witch 12B Heretic
Stellar · mradermacher
Params12.2B
Context128K
Best fitQ6_K 11.9 GB
GGUF
JI
JiRackUltra 7b
Jirackultra · CMSManhattan
Params7.62B
Context128K
Best fitQ8_0 9.1 GB
ReasoningTool use
QW
Qwen2.5 Coder 7B Instruct Uncensored
Qwen · Fbjfhvgv
Params7.62B
Context32K
Best fitQ8_0 9.1 GB
Coding
SO
SOLAR 10.7B Instruct v1.0 uncensored
Solar · TheBloke
Params10.7B
Context4K
Best fitQ6_K 10.9 GB
GGUF
SP
Spark X2.5 4B uncensored
Spark · InfinimindCreations
Params4.1B
Context1024K
Best fitBF16 9.9 GB
GGUF
QW
Qwen3 0.6B Base
Qwen · mradermacher
Params596M
Context32K
Best fitF16 2.6 GB
GGUF
IN
Ingot VIII 27B Q2
Ingot · dendriteholdings
Params26.9B
Context256K
Smallest7.2 GB
ReasoningTool use
GE
gemma 4 E4B it heretic QAT
Gemma · SC117
Params7.46B
Context128K
Best fitQ4_K_XL 6.2 GB
CodingVision
GE
Gemma 3 270m It Qat Q4_0 Unquantized
Gemma · ggml-org
Params268M
Context32K
Best fitQ4_0 0.9 GB
GGUF
QW
Qwen2.5 VL 32B Instruct
Qwen · mradermacher
Params32.8B
Context125K
Best fitIQ2_XXS 11.7 GB
Vision
GE
Gemma 3 12b It Heretic
Gemma · mradermacher
Params11.8B
Context128K
Best fitQ5_K_S 12.0 GB
Vision
KE
Kev-0.8B
Kev · ggml-org
Params753M
Context256K
Best fitBF16 2.4 GB
GGUF
MO
Moonlight 16B A3B Instruct
Moonlight · mmnga
Params16B
Context8K
Best fitQ4_0 11.8 GB
GGUF
GE
Gemma-3N-E2B-It
Gemma · unsloth
Params4.46B
Context32K
Best fitF16 9.9 GB
Vision
QW
Qwen3.8 27B Heretic Ara
Qwen · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
GGUF
RA
RakutenAI 7B Chat
Rakutenai · mradermacher
Params7.37B
Context32K
Best fitQ8_0 9.4 GB
GGUF
QW
Qwen2.5-VL-7B-Instruct
Qwen · Mungert
Params7.6B
Context125K
Best fitBF16 10.1 GB
Vision
LL
Llama-3-Groq-8B-Tool-Use
Llama · lmstudio-community
Params8B
Context8K
Best fitQ8_0 10.1 GB
Tool use
QW
Qwen3.8 27B Heretic Abliterated Uncensored
Qwen · mradermacher
Params27B
Context256K
Best fitIQ2_S 12.0 GB
GGUF
TI
TildeOpen 30B Instruct LV
Tildeopen · mradermacher
Params30.7B
Context64K
Best fitIQ2_XS 11.9 GB
GGUF
QW
Qwen3.5 4B MultiDistill 3xMerge UNCENSORED Heretic
Qwen · mradermacher
Params4.21B
Context256K
Best fitQ6_K 5.1 GB
Reasoning
FL
flux 3 image klein prompt upsampler
Flux · prithivMLmods
Params8.95B
Context256K
Best fitQ8_0 11.1 GB
Vision
FR
FrogNano 4B Heretic
Frognano · mradermacher
Params4.21B
Context256K
Best fitQ6_K 5.1 GB
CodingRoleplayTool use
IN
Ingot III 27B Q2
Ingot · dendriteholdings
Params26.9B
Context256K
Smallest7.2 GB
ReasoningTool use
QW
Qwen3.8-27B
Qwen · aiartorious
Params27.3B
Context256K
Best fitIQ2_S 11.9 GB
Vision
QW
Qwen3.5 2B Base Heretic
Qwen · mradermacher
Params1.88B
Context256K
Best fitQ6_K 2.5 GB
GGUF
GR
Granite 3.1 1b A400M Instruct
Granite · bartowski
Params1.33B
Context128K
Best fitF16 3.6 GB
GGUF
QW
Qwen3.8 Flash Next Rulith EXL3
Qwen · Rulith
Params177B
Context256K
Smallest2.6 GB
ReasoningTool useVision
YI
01-ai_yi-6b-200k
Yi · TheBloke
Params6.06B
Context195K
Best fitQ8_0 7.5 GB
GGUF

Other memory sizes

Keep browsing