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.
IN
InternVL3 8B Instruct
Internvl · ggml-org
Params7.61B
Context32K
Best fitQ8_0 9.1 GB
TO
ToriiGate v0.4 7B
Toriigate · mradermacher
Params7.62B
Context32K
Best fitQ8_0 9.1 GB
QW
Qwen3 1.7B Abliterated
Qwen · mradermacher
Params1.72B
Context40K
Best fitF16 4.9 GB
DA
G4 Dark Soul 26B A4B
Dark · bartowski
Params25.2B
Context256K
Q4_K_M17.0 GB
LL
Llama 3.1 8B Stheno v3.4
Llama · Lewdiculous
Params8B
Context128K
Best fitQ8_0 10.1 GB
MI
Mistral Pygmalion 7B
Mistral · TheBloke
Params6.74B
Context4K
Best fitQ8_0 12.0 GB
BO
Boundary 4x7b MoE i1
Boundary · mradermacher
Params24.2B
Context32K
Best fitQ3_K_S 12.0 GB
QW
Qwen2.5 Coder 1.5B Instruct
Qwen · QuantFactory
Params1.54B
Context32K
Best fitQ8_0 2.4 GB
RW
rwkv7 g1h 1.5b i1
Rwkv · RemySkye
Params1.53B
Context1024K
Best fitQ6_K 2.0 GB
QW
Qwen3.5 9B Harmonic
Qwen · DJLougen
Params8.95B
Context256K
Best fitQ8_0 11.1 GB
HO
K2 Horizon 3.7B Heretic
Horizon · mradermacher
Params5.06B
Context512K
Best fitQ6_K 5.9 GB
QW
Qwen3.8 27B GSQ RCO IQ3 S recovered
Qwen · Joakimpalm-Zen
Params26.9B
Context256K
Best fitQ8_0 5.8 GB
LL
code Llama 2 13B i1
Llama · mradermacher
Params13B
Context16K
Best fitIQ2_M 11.7 GB
HO
K2 Horizon 7B Candor Uncensored
Horizon · candor-lab
Params9B
Context512K
Best fitQ4_K_M 7.3 GB
PA
Pantheon Proto RP 1.8 30B A3B
Pantheon · bartowski
Params30.5B
Context32K
Best fitIQ2_M 11.7 GB
QW
Qwen3.8 9B Distill Uncen Heretic
Qwen · mradermacher
Params9.2B
Context256K
Best fitQ8_0 11.4 GB
MI
Solstice Mixtral v1 i1
Mistral · mradermacher
Params46.7B
Context32K
Best fitIQ1_S 11.6 GB
GE
Gemma 4 26B A4B It SOMPOA Heresy
Gemma · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
MI
OpenHermes-2.5-Mistral-7B-x2
Mistral · mradermacher
Params7.24B
Context32K
Best fitQ6_K 7.5 GB
MI
MiniCPM V 2 6
MiniCPM · bartowski
Params7.6B
Context32K
Best fitQ8_0 9.1 GB
QW
Qwen3-14B-128K
Qwen · unsloth
Params14.8B
Context128K
Best fitQ4_1 11.2 GB
QW
Qwythos 9B v2
Qwythos · mradermacher
Params9.2B
Context1024K
Best fitQ6_K 9.2 GB
ID
ideogram4 turbo
Ideogram · ChrisColeTech
Params9.28B
Context256K
Best fitQ8_0 11.8 GB
SK
Skyfall 31B v4.2 Heretic
Skyfall · mradermacher
Params31.4B
Context128K
Best fitIQ2_XS 11.8 GB
MI
severian_anima-phi-neptune-mistral-7b
Mistral · TheBloke
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
GR
Granite Guardian 4.1 8b
Granite · ibm-granite
Params8.38B
Context128K
Best fitQ8_0 10.8 GB
QW
PopiT Qwen3 4B Medical SFT 1128
Qwen · mradermacher
Params4B
Context40K
Best fitF16 9.8 GB
PA
Parakeet TDT 0.6B v2 English Hebrew Codeswitching
Parakeet · danielrosehill
Params618M
Context—
Best fitF16 1.9 GB
NE
NeoHorse 1 9 Uncensored
Neohorse · mradermacher
Params8.95B
Context256K
Best fitQ6_K 9.0 GB
DA
Dark Scarlett 27B v3.0
Dark · ReadyArt
Params27.3B
Context256K
Q4_K_M23.5 GB