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.
AN
anthracite org magnum 12b v2
Anthracite · RichardErkhov
Params12.2B
Context—
Best fitIQ3_M 6.9 GB
DE
DeepSeek-Coder-V2-Lite-Instruct
DeepSeek · bartowski
Params15.7B
Context160K
Best fitIQ4_XS 11.3 GB
NE
Nemotron 3.5 Bolt E4B
Nemotron · nvidia
Params7.52B
Context64K
Best fitQ4_K_M 8.1 GB
TE
Ternary Bonsai 2 27B Uncensored Heretic v2
Ternary · OS-Software
Params27B
Context256K
Smallest5.9 GB
MI
models--mistralai--Mistral-7B-Instruct-v0.3
Mistral · MaziyarPanahi
Params7.25B
Context32K
Best fitQ8_0 9.3 GB
JI
Jina Embeddings v5 Text Nano Retrieval
Jina · jinaai
Params212M
Context8K
Best fitF16 1.2 GB
MI
Ministral 3 3B Instruct 2512
Mistral · mistralai
Params3.43B
Context256K
Best fitBF16 8.2 GB
CO
C4Ai Command R7B 12 2024
Command R · bartowski
Params8B
Context8K
Best fitQ8_0 10.1 GB
QW
Qwen3.6 27B
Qwen · bartowski
Params27.3B
Context256K
Best fitQ8_0 5.8 GB
QW
Qween3 4B thinking finetune
Qween · pramodlohra
Params4B
Context256K
Best fitQ4_K_M 4.2 GB
LI
Ling 3.0 Tiny
Ling · bartowski
Params7.89B
Context128K
Best fitQ6_K_L 11.9 GB
QW
Qwen3.8 27B Heretic GSQ RCO
Qwen · 0bserverx
Params27B
Context256K
Best fitIQ2_S 11.9 GB
PH
Phi 3.5 Mini Instruct
Phi · MaziyarPanahi
Params3.82B
Context128K
Best fitQ8_0 7.8 GB
QW
Qwen2.5 Coder 14B Instruct
Qwen · bartowski
Params14.8B
Context32K
Best fitQ4_K_L 11.7 GB
QW
Qwen3.5 2B
Qwen · bartowski
Params1.94B
Context256K
Best fitBF16 4.8 GB
JI
Jina Embeddings v5 Text Small Retrieval
Jina · jinaai
Params596M
Context40K
Best fitF16 2.6 GB
VO
Voxtral Mini 3B 2507
Voxtral · ggml-org
Params4B
Context128K
Best fitQ4_K_M 4.0 GB
QW
Qwen3 1.7B
Qwen · bartowski
Params2.03B
Context32K
Best fitBF16 5.5 GB
LF
LFM2.5 2.6B DSpark Draft v1
Lfm · LiquidAI
Params328M
Context125K
Best fitF16 1.2 GB
MI
Ministral 3 8B Instruct 2512
Mistral · mistralai
Params8.49B
Context256K
Best fitQ8_0 10.7 GB
CY
Cydonia 24B v4.3
Cydonia · bartowski
Params23.6B
Context128K
Best fitIQ3_XS 11.7 GB
QW
Qwen2.5 Coder 7B Instruct Abliterated
Qwen · bartowski
Params7.62B
Context32K
Best fitQ8_0 9.1 GB
TR
Translategemma 12b It
Translategemma · mradermacher
Params11.8B
Context128K
Best fitQ5_K_S 12.0 GB
QW
Qwen3 0.6B
Qwen · ggml-org
Params752M
Context40K
Best fitF16 2.9 GB
QW
Qwen3.5 9B DeepSeek V4 Flash
Qwen · Jackrong
Params8.95B
Context256K
Best fitQ8_0 11.1 GB
MI
MiniCPM5 1B
MiniCPM · openbmb
Params1.08B
Context128K
Best fitF16 2.9 GB
QW
Qwen2.5 VL 7B Instruct
Qwen · mradermacher
Params7.62B
Context125K
Best fitQ8_0 9.1 GB
GR
ibm granite granite 20b code base
Granite · RichardErkhov
Params1.9B
Context—
Best fitQ3_K_S 10.5 GB
LL
CreativeWriter Llama3.2 3B
Llama · theprint
Params3.21B
Context128K
Best fitF16 7.9 GB
QW
Qwen3.8 27B Uncensored OrcaRouter
Qwen · chimingw
Params27.3B
Context256K
Best fitQ8_0 5.8 GB