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.
HO
Holo 3.1 9B
Holo · mradermacher
Params8.95B
Context256K
Best fitQ8_0 11.1 GB
QW
Dongfangshuo Qwen3.8 27B NSFW v4
Qwen · mradermacher
Params27B
Context256K
Best fitIQ2_S 12.0 GB
MI
Codestral-22B-v0.1
Mistral · bartowski
Params22.2B
Context32K
Best fitQ3_K_S 12.0 GB
QW
Qwen3.8 27B Abliterated
Qwen · mradermacher
Params27B
Context256K
Best fitIQ2_S 12.0 GB
MI
teknium_openhermes-2-mistral-7b
Mistral · TheBloke
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
PP
pplx decider flash gguf v1.2
Pplx · perplexity-ai
Params4.84B
Context256K
Best fitQ8_0 6.7 GB
QW
Qwen3.8 14B Instruct Turbo
Qwen · mradermacher
Params14.7B
Context256K
Best fitQ5_K_S 11.9 GB
LL
SageV2 8B LongContext NSFW RP
Llama · sinhal
Params8.03B
Context128K
Best fitQ8_0 10.1 GB
DE
DeepSeek R1 Distill Qwen 7B Uncensored
DeepSeek · mradermacher
Params7.61B
Context128K
Best fitQ8_0 9.1 GB
LL
ultravox v0 5 llama 3 2 1b
Llama · ggml-org
Params1.24B
Context128K
Best fitQ8_0 2.1 GB
SP
Spark X2.5 4B Abliterated
Spark · SC117
Params4.11B
Context1024K
Best fitBF16 9.9 GB
MI
Ministral 3 14B Reasoning 2512
Mistral · mistralai
Params13.5B
Context256K
Best fitQ5_K_M 11.5 GB
MI
maywell Mistral ko 7B v0.1
Mistral · RichardErkhov
Params1.5B
Context—
Best fitIQ3_XS 4.0 GB
QW
Qwen3.5 9B Claude 4.6 HighIQ THINKING HERETIC UNCENSORED
Qwen · mradermacher
Params8.95B
Context256K
Best fitQ8_0 11.1 GB
TI
TIPO 200M Ft
Tipo · KBlueLeaf
Params203M
Context2K
Best fitF16 1.4 GB
DE
DeepSeek-V2-Lite-Chat
DeepSeek · legraphista
Params15.7B
Context160K
Best fitIQ4_NL 11.7 GB
SA
Sage A1.5 Heretic Abliterated Uncensored
Sage · mradermacher
Params34.7B
Context256K
Best fitIQ2_S 11.8 GB
LF
LFM2 350M
Lfm · LiquidAI
Params354M
Context125K
Best fitF16 1.7 GB
QW
Qwopus3.5 4B Coder MTP HF
Qwen · Jackrong
Params334M
Context256K
Best fitBF16 10.3 GB
QW
Qwen3 235B A22B Instruct 2507
Qwen · bartowski
Params235B
Context256K
Q4_K_M142.6 GB
QW
Dongfangshuo Qwen3.8 27B NSFW Novel
Qwen · mradermacher
Params27B
Context256K
Best fitIQ2_S 12.0 GB
RO
Rocinante 12B v1.1
Rocinante · TheDrummer
Params12.2B
Context1000K
Best fitQ6_K 11.9 GB
HO
Holo4 35B A3B
Holo · bartowski
Params34.7B
Context256K
Best fitIQ2_XXS 12.0 GB
LA
latxa-7b-v1.2
Latxa · mradermacher
Params6.74B
Context4K
Best fitQ8_0 12.0 GB
QW
Qwen3.5 9B
Qwen · SoAIHQ
Params9.2B
Context256K
Best fitQ8_0 11.4 GB
IN
Ingot IV 27B Q2
Ingot · dendriteholdings
Params26.9B
Context256K
Smallest5.9 GB
JI
Hf Jinen v2 Small
Jinen · togatogah
Params110M
Context1K
Best fitF16 1.0 GB
LI
Ling 3.0 tiny
Ling · NANI-Nithin
Params7.89B
Context128K
Best fitQ6_K 11.4 GB
RO
Rocinante 12B v1.1
Rocinante · bartowski
Params12.2B
Context1000K
Best fitQ6_K 11.9 GB
MI
Source Hf Minicpm V 4.7 1b
MiniCPM · ngquocvinh
Params1.01B
Context256K
Best fitQ8_0 2.0 GB