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.
QW
Qwen3.8 2B Distill Heretic
Qwen · mradermacher
Params1.88B
Context256K
Best fitQ6_K 2.5 GB
MI
Voxtral Small 24B 2507
Mistral · bartowski
Params23.6B
Context128K
Best fitIQ3_XS 11.7 GB
AU
Audar ASR V1 Turbo
Audar · audarai
Params2.03B
Context64K
Q4_K_M1.3 GB
QW
Qwen3 8B Socratic SFT
Qwen · mradermacher
Params8.19B
Context40K
Best fitQ6_K 8.4 GB
QW
Crow 9B HERETIC 4.6
Qwen · Crownelius
Params8.95B
Context256K
Best fitQ8_0 11.1 GB
GE
Skaldic Gemma 4 E4B
Gemma · mradermacher
Params7.46B
Context128K
Best fitQ6_K 8.1 GB
QW
Qwen2-1.5B-Instruct
Qwen · legraphista
Params1.54B
Context32K
Best fitBF16 3.8 GB
AI
jondurbin_airoboros-m-7b-3.1
Airoboros · TheBloke
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
JA
Jais-3-7B
Jais · mradermacher
Params9B
Context512K
Best fitQ6_K 9.1 GB
QW
Wrench 9B Q4 K M
Qwen · ClankLabs
Params8B
Context256K
Best fitQ4_K_M 7.2 GB
UM
Umievo-itr012-Gleipnir-7B
Umievo · mmnga
Params7.24B
Context8K
Best fitQ8_0 9.3 GB
KI
Kisoku 1.6b Chat
Kisoku · mradermacher
Params1.6B
Context128K
Best fitQ6_K 2.2 GB
HU
Hunyuan 1.8B Instruct
Hunyuan · bartowski
Params1.79B
Context256K
Best fitBF16 4.6 GB
GR
Granite 3b Code Base 128k
Granite · RichardErkhov
Params3.48B
Context125K
Best fitQ8_0 6.9 GB
QW
Qwen2.5 7B Instruct Uncensored
Qwen · WSDW
Params7.62B
Context32K
Best fitQ4_K_M 5.7 GB
QW
Qwen3.8 27B Humanlike Chat
Qwen · Guile
Params27B
Context256K
Best fitF32 10.1 GB
GE
Gemma 4 E4B It Apostate
Gemma · mradermacher
Params8.13B
Context128K
Best fitQ6_K 8.6 GB
AU
Audar TTS V1 Turbo
Audar · audarai
Params1.64B
Context32K
Best fitQ8_0 2.5 GB
QI
QiMing Holos Plus 8B
Qiming · mradermacher
Params8B
Context128K
Best fitQ6_K 8.2 GB
NO
North Mini Code 1.0 Uncensored Heretic
North · mradermacher
Params30.5B
Context488K
Best fitQ2_K_S 11.9 GB
LL
samantha-dolphin-llama-3
Llama · mradermacher
Params7.24B
Context32K
Best fitQ6_K 7.5 GB
HE
Hemmingway 1 Heretic MTP V3 Final
Hemmingway · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
MY
MythoLogic Mini 7B
Mythologic · TheBloke
Params6.74B
Context4K
Best fitQ8_0 12.0 GB
YO
Youri 7b Instruction
Youri · mradermacher
Params6.74B
Context4K
Best fitQ6_K 10.3 GB
BR
Breeze-7B-Instruct-v0_1
Breeze · RichardErkhov
Params7.49B
Context32K
Best fitQ8_0 9.5 GB
GE
Gemma4 26B A4B Uncensored HauhauCS 1M
Gemma · satgeze
Params25.2B
Context1024K
Q4_K_M16.8 GB
QW
Qwen3.8 9B
Qwen · Atomic-Germ
Params9.2B
Context256K
Best fitQ8_0 11.4 GB
GR
Granite 4.0 350m
Granite · ibm-granite
Params352M
Context32K
Best fitBF16 2.1 GB
GI
ai girlfriend natsume
Girlfriend · TAOTAO777
Params27B
Context256K
Best fitQ6_K 8.6 GB
SA
SauerkrautLM UNA SOLAR Instruct
Sauerkrautlm · TheBloke
Params10.7B
Context4K
Best fitQ6_K 10.9 GB