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
GE
gemma-4-26B-A4B-it
Gemma · ggml-org
Params450M
Context256K
Best fitBF16 2.4 GB
Vision
QW
Qwen3.6-27B
Qwen · unsloth
Params27B
Context256K
Best fitIQ2_XXS 12.0 GB
Vision
QW
qwen2.5-0.5b-instruct
Qwen · Qwen
Params630M
Context32K
Q4_K_M0.5 GB
GGUF
QW
Qwythos-9B-v2
Qwythos · empero-ai
Params8.95B
Context1024K
Best fitQ8_0 11.4 GB
ReasoningTool useVision
SP
Spark X2.5 4B
Spark · XHToken
Params4.1B
Context1024K
Q4_K_M2.6 GB
GGUF
SQ
sqlcoder 7b 2
Sqlcoder · defog
Params6.74B
Context16K
Best fitQ5_K_M 9.6 GB
Coding
QW
Qwythos 9B Claude Mythos 5 1M
Qwythos · empero-ai
Params8.95B
Context1024K
Best fitQ8_0 11.4 GB
ReasoningTool useVision
QW
Qwen3 14B Awq Compatible Instruct
Qwen · Qwen
Params14.8B
Context40K
Best fitQ4_K_M 10.8 GB
GGUF
SP
Spark X2.5 4B
Spark · abenzerps
Params4.1B
Context1024K
Best fitQ8_0 6.1 GB
GGUF
TH
Thomson 1.0 Small
Thomson · bartowski
Params34.7B
Context256K
Best fitIQ2_XS 12.0 GB
Vision
OR
Ornith 1.5 9B OBLITERATED
Ornith · OBLITERATUS
Params9.2B
Context256K
Best fitQ8_0 11.4 GB
Vision
GE
Gemmable 4 12B MTP
Gemma · Mia-AiLab
Params11.9B
Context256K
Best fitQ6_K 11.4 GB
Reasoning
LF
LFM2.5 Audio 1.5B JP
Lfm · LiquidAI
Params190M
Context125K
Best fitF32 5.3 GB
Vision
TE
Ternary Bonsai 8B
Ternary · prism-ml
Params8.19B
Context64K
Best fitQ2_0 4.0 GB
GGUF
QW
Qwen2.5 Coder 7B Instruct GGUF
Qwen · Qwen
Params15B
Context128K
Best fitQ5_K_M 11.9 GB
Coding
JA
Jan-v3.5-4B
Jan · janhq
Params4.4B
Context256K
Q4_K_M2.7 GB
GGUF
HY
Hy MT2 1.8B
tencent
Params1.79B
Context256K
Best fitQ8_0 2.9 GB
GGUF
LF
LFM2.5 1.2B Instruct
Lfm · LiquidAI
Params1.17B
Context125K
Best fitBF16 3.9 GB
GGUF
QW
Qwen3.6 14B A3B FableVibes Hf
Qwen · tvall43
Params13.8B
Context256K
Best fitQ5_K_M 11.0 GB
CodingReasoningTool use
QW
Qwen3.8 27B Uncensored Cyber agentic imatrix
Qwen · cyjin-yl
Params31B
Context—
Smallest0.0 GB
Vision
SP
Spark X2.5 4B Heretic jp
Spark · soyaakinohara
Params4.1B
Context1024K
Best fitBF16 9.9 GB
Tool use
LF
LFM2.5 230M
Lfm · LiquidAI
Params230M
Context125K
Best fitBF16 1.4 GB
GGUF
ME
Mellum2.1-12B-A2.5B-Thinking
Mellum · JetBrains
Params12.1B
Context128K
Best fitQ6_K 11.8 GB
Reasoning
QW
Bonsai-27B-dspark
Qwen · prism-ml
Params3.6B
Context4K
Best fitBF16 7.9 GB
Vision
KA
KAT Coder V2.5 Dev
Kat · bartowski
Params34.7B
Context256K
Best fitIQ2_XS 12.0 GB
Coding
MI
MiniCPM5 2B
MiniCPM · openbmb
Params2.52B
Context128K
Best fitF16 5.9 GB
CodingTool use
QW
Qwen3.8 27B
Qwen · bartowski
Params27.3B
Context256K
Best fitIQ2_XS 11.8 GB
Vision
QW
Huihui Qwen3.8 Flash Next abliterated v2
Qwen · huihui-ai
Params177B
Context—
Smallest1.2 GB
ReasoningVision
MI
MiniCPM V 4.7 35B A3B
MiniCPM · openbmb
Params34.7B
Context256K
Best fitF16 2.0 GB
ReasoningTool useVision
GR
Granite 4.2 3b
Granite · ibm-granite
Params3.66B
Context128K
Best fitBF16 8.5 GB
GGUF

Other memory sizes

Keep browsing