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.
MI
mistralai_mistral-7b-v0.1
Mistral · TheBloke
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
MI
Mistral Nemo Instruct 2407 12B Thinking M Claude Opus High Reasoning
Mistral · mradermacher
Params12.2B
Context1000K
Best fitQ6_K 11.9 GB
GR
TwIL LM3 Pro
Granite · webAI-Official
Params3.66B
Context128K
Best fitF16 8.5 GB
HE
Hemmingway 1
Hemmingway · botp
Params27.3B
Context256K
Best fitIQ2_XS 11.8 GB
QW
Qwen1.5-0.5B-Chat-AWQ-fp16
Qwen · Qwen
Params620M
Context32K
Best fitQ8_0 2.0 GB
HU
HunyuanOCR
Hunyuanocr · prithivMLmods
Params539M
Context128K
Best fitF32 3.5 GB
QW
Qwen3 4B
Qwen · lmstudio-community
Params4B
Context32K
Best fitQ8_0 6.0 GB
MA
MN 12B Mag Mell R1
Mag · bartowski
Params12.2B
Context1000K
Best fitQ6_K 11.9 GB
HO
K2 Horizon MoVA 36B A4B Uncensored
Horizon · mradermacher
Params37.4B
Context512K
Best fitIQ1_M 10.8 GB
JE
Jebadiah 9b v2
Jebadiah · frontier-infra
Params9.2B
Context256K
Best fitQ8_0 11.4 GB
OP
openchat-3.6-8b-20240522
Openchat · legraphista
Params8B
Context8K
Best fitQ8_0 10.1 GB
OL
allenai_olmOCR 2 7B 1025
OLMo · lmstudio-community
Params7.62B
Context125K
Best fitQ8_0 9.1 GB
QW
Qwen3 Sex
Qwen · ystemsrx
Params4B
Context256K
Best fitBF16 9.8 GB
QW
Swift Qwen3.8 27b
Qwen · bartowski
Params27.3B
Context256K
Best fitIQ2_XS 11.8 GB
QW
Qwen3.5 4B Claude 4.6 Opus Reasoning Distilled v2
Qwen · Jackrong
Params4.2B
Context256K
Best fitQ8_0 6.1 GB
HU
Hunyuan-MT-7B
Hunyuan · Mungert
Params7.5B
Context256K
Best fitQ8_0 9.6 GB
QW
Jev Style Qwen3.5 2B Decision
Qwen · chaoliangUNSW
Params1.94B
Context256K
Best fitBF16 4.8 GB
QW
Qwen Image 2.1 Text Encoder
Qwen · darrellbest
Params8.2B
Context256K
Best fitQ8_0 10.4 GB
PH
phi 4
Phi · bartowski
Params14.7B
Context16K
Best fitQ4_K_L 11.6 GB
GE
Ablation 188 Gemma3.Webnovels.Test.Gemma 3 12b
Gemma · mradermacher
Params11.8B
Context128K
Best fitQ5_K_S 12.0 GB
SM
SmolLM2 135M Instruct
SmolLM · mradermacher
Params135M
Context8K
Best fitQ2_K 0.8 GB
QW
Qwen2.5-14B-Instruct-1M
Qwen · Mungert
Params14.8B
Context986K
Best fitQ4_1 11.4 GB
QW
Qwen3.8 27B
Qwen · KikoCis
Params26.9B
Context256K
Best fitIQ2_XS 11.8 GB
MI
Mistral-7B-Instruct-v0.3
Mistral · lmstudio-community
Params7.25B
Context32K
Best fitQ8_0 9.3 GB
MI
MiniCPM V 4.7 1B abliterated heretic
MiniCPM · Abiray
Params1.01B
Context256K
Best fitQ8_0 2.0 GB
QW
Sakura 1.5B Qwen2.5 v1.0 GGUF IMX
Qwen · shing3232
Params1.78B
Context128K
Smallest1.3 GB
QW
Qwen3.5 9B Heretic
Qwen · darrellbest
Params9.2B
Context256K
Best fitQ8_0 11.4 GB
LA
m51Lab MiniMax M2.7 REAP 139B A10B
Lab · mradermacher
Params139B
Context192K
Q4_K_M84.2 GB
GE
avemio digital gemma 2b Sft pretrain 6000 steps merge
Gemma · RichardErkhov
Params2.5B
Context8K
Best fitQ4_K 2.3 GB
QW
Qwen2.5 7B Instruct
Qwen · paultimothymooney
Params7.62B
Context32K
Best fitQ4_K_M 5.7 GB