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
Mica v0.5 4B
Qwen · sky7350
Params4.21B
Context256K
Best fitBF16 10.0 GB
ReasoningTool use
ST
StartLux Decision v1 4B Q4 K M
Startlux · startlux-models
Params4.21B
Context256K
Best fitQ4_K_M 4.3 GB
GGUF
JA
Jan v2 VL med
Jan · janhq
Params8.2B
Context256K
Best fitQ8_0 10.4 GB
Vision
QW
Qwen3.5 2B Uncensored Zero Refusal SOMA
Qwen · AkaumiKaede
Params1.88B
Context256K
Best fitF16 4.7 GB
RoleplayVision
LI
Ling Flash 2.0
Ling · bartowski
Params103B
Context32K
Q4_K_M62.6 GB
GGUF
AM
amalia-llm/AMALIA-9B-0626-DPO
Amalia · layerx-labs
Params9.15B
Context32K
Best fitQ8_0 11.6 GB
GGUF
QW
Qwen3.5 9b Uncensored
Qwen · mradermacher
Params8.95B
Context256K
Best fitQ6_K 8.9 GB
Tool use
RA
MS Raven 24B v1
Raven · mradermacher
Params23.6B
Context128K
Best fitIQ3_XS 11.7 GB
Roleplay
GE
Gemma 3 12b It Vl Kimi V2 Heretic Uncensored Thinking
Gemma · mradermacher
Params11.8B
Context128K
Best fitQ5_K_S 12.0 GB
ReasoningVision
LF
LFM3-1.7B
Lfm · AtomicChat
Params1.73B
Context256K
Best fitQ8_0 4.0 GB
ReasoningTool use
LL
Meta Llama 3.1 8B Instruct
Llama · joshnader
Params8B
Context128K
Best fitQ4_K_M 6.5 GB
GGUF
CH
AA Chameleon 7b Base
Chameleon · mradermacher
Params7B
Context4K
Best fitQ6_K 10.6 GB
GGUF
WR
Wren
Wren · ohmysimo
Params117B
Context256K
Q4_K_M77.6 GB
GGUF
QW
MiMo V2.6 Distill Qwen 9B Heretic
Qwen · mradermacher
Params8.95B
Context256K
Best fitQ6_K 8.9 GB
CodingReasoningRoleplay
QW
Qwen3.8-27B
Qwen · xrachelburns
Params27.3B
Context256K
Best fitIQ2_S 11.9 GB
Vision
HU
Hunyuan 7B Instruct
Hunyuan · bartowski
Params7.5B
Context256K
Best fitQ8_0 9.6 GB
GGUF
QW
Huihui Qwen3.8 27B Abliterated
Qwen · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
GGUF
GE
Gemma 3n E4B It
Gemma · bartowski
Params6.9B
Context32K
Best fitQ8_0 8.4 GB
GGUF
QW
Qwen3 Coder 30B A3B Instruct RTPurbo
Qwen · mradermacher
Params30.5B
Context256K
Best fitQ2_K_S 11.8 GB
Coding
LL
CodeLlama 7b Python Hf
Llama · mradermacher
Params6.74B
Context16K
Best fitQ6_K 10.3 GB
Coding
TO
Torchcast Decision 27b
Torchcast · mradermacher
Params27B
Context256K
Best fitIQ2_S 12.0 GB
GGUF
AR
Artex Coder 7b
Artex · mradermacher
Params7.62B
Context32K
Best fitQ6_K 7.2 GB
Coding
QW
Qwen25 Coder 3b Claude
Qwen · ryzdfm
Params3.09B
Context32K
Best fitQ4_K_M 2.7 GB
CodingReasoning
MT
Mtrini SVL 2.0
Mtrini · mradermacher
Params8.95B
Context256K
Best fitQ6_K 9.0 GB
ReasoningTool use
QW
Rice Cracker Qwen3.5 0.8B Abliterated Base
Qwen · mradermacher
Params752M
Context256K
Best fitQ4_1 1.5 GB
Coding
NO
nousresearch_nous-capybara-7b-v1.9
Nous · TheBloke
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
GGUF
UN
UnslopNemo 12B v4.1
Unslopnemo · TheDrummer
Params12.2B
Context1000K
Best fitQ6_K 11.9 GB
GGUF
OV
OvisOCR2
Ovisocr · Abiray
Params752M
Context256K
Best fitF16 2.4 GB
Vision
GR
Granite 4.2 8b
Granite · bartowski
Params8.79B
Context128K
Best fitQ8_0 11.2 GB
ReasoningTool use
NO
Nous Hermes 2 SOLAR 10.7B
Nous · TheBloke
Params10.7B
Context4K
Best fitQ6_K 10.9 GB
Tool use

Other memory sizes

Keep browsing