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.
LL
CodeLlama 34b Python Hf
Llama · mradermacher
Params33.7B
Context16K
Best fitIQ2_XXS 11.1 GB
PH
phi3.5 gutenberg 4B i1
Phi · mradermacher
Params3.82B
Context128K
Best fitQ6_K 6.9 GB
SA
vagosolutions_sauerkrautlm-7b-hero
Sauerkrautlm · TheBloke
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
CY
TheDrummer Cydonia 24B v2
Cydonia · bartowski
Params23.6B
Context32K
Best fitIQ3_XS 11.7 GB
GE
gemma 4 hacking
Gemma · deathafteryou
Params7.5B
Context128K
Best fitQ4_K_M 7.2 GB
QW
dnotitia_Smoothie Qwen3 14B
Qwen · Alcoft
Params14.8B
Context40K
Best fitQ5_K_XS 12.0 GB
LL
Llama3-ChatQA-1.5-8B
Llama · legraphista
Params8B
Context8K
Best fitQ8_0 10.1 GB
TM
Tmax v1.1 9b
Tmax · mradermacher
Params8.95B
Context256K
Best fitQ6_K 8.9 GB
ED
vllm-d3-edge
Edge · ggml-org
Params748M
Context256K
Best fitBF16 2.2 GB
QW
Qwen2.5 Coder 14B Instruct Uncensored
Qwen · BlossomsAI
Params14.8B
Context32K
Best fitQ4_K_M 11.1 GB
ST
stablelm tuned alpha 7b i1
Stablelm · mradermacher
Params7.87B
Context4K
Best fitQ6_K 10.2 GB
ST
Starcoder
StarCoder · mradermacher
Params15.8B
Context8K
Best fitQ5_K_S 11.8 GB
GU
Guanaco 13B Uncensored i1
Guanaco · mradermacher
Params13B
Context4K
Best fitIQ2_M 11.7 GB
AL
ALoDLM 8B
Alodlm · mradermacher
Params8.19B
Context40K
Best fitQ6_K 8.4 GB
QW
Logics SWE Qwen3.6 27B
Qwen · mradermacher
Params26.9B
Context256K
Best fitIQ2_S 12.0 GB
QW
Qwen3 14B
Qwen · lm-kit
Params14.8B
Context40K
Best fitQ4_K_M 10.8 GB
OR
Ornith-1.5-9B-Uncensored
Ornith · vonvonhero
Params8.95B
Context256K
Best fitQ8_0 11.1 GB
FI
Fimbulvetr 11B v2 i1
Fimbulvetr · mradermacher
Params10.7B
Context4K
Best fitQ6_K 11.1 GB
FR
FrogNano 4B 2609
Frognano · webmp3
Params4.33B
Context256K
Smallest2.0 GB
QW
Qwen3 1.7B
Qwen · gaianet
Params2.03B
Context40K
Best fitF16 5.5 GB
ST
stable code 3b
Stable · TheBloke
Params2.8B
Context16K
Best fitQ8_0 6.2 GB
OL
OLMo 2 1124 7B Instruct
OLMo · bartowski
Params7.3B
Context4K
Best fitQ6_K_L 11.0 GB
JA
Jan-v3-4b-base-instruct
Jan · janhq
Params4.4B
Context256K
Q4_K_M2.7 GB
WE
WeVisOne VL 2B
Wevisone · mradermacher
Params2.03B
Context256K
Best fitF16 5.5 GB
GR
Granite 4.2 3b
Granite · bartowski
Params3.66B
Context128K
Best fitBF16 8.5 GB
HE
Hermes 4.3 36B Heretic
Hermes · mradermacher
Params36.2B
Context512K
Best fitIQ1_M 11.4 GB
MI
WikiHow Mistral Instruct 7B
Mistral · mradermacher
Params7.24B
Context32K
Best fitQ8_0 9.4 GB
LL
Llama 3.2 3B Instruct Abliterated
Llama · mradermacher
Params3.61B
Context128K
Best fitF16 8.7 GB
RI
Ringg Router E2B
Ringg · bartowski
Params4.63B
Context128K
Best fitBF16 10.4 GB
DP
openaccess-ai-collective_dpopenhermes-7b-v2
Dpopenhermes · TheBloke
Params7.24B
Context32K
Best fitQ8_0 9.3 GB