GGUF models that fit in 8 GB
151917 GGUF language models have at least one quant whose estimated memory use is 8 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.
DE
Qwen3 30B A3B Deepseek Distill Instruct 2507
DeepSeek · mradermacher
Params30.5B
Context256K
Best fitIQ1_S 7.7 GB
LL
nousresearch_yarn-llama-2-7b-64k
Llama · TheBloke
Params6.74B
Context64K
Best fitQ3_K_S 7.7 GB
MI
MiniCPM5-2B-Claude-Fable5-1-Thinking
MiniCPM · GnLOLot
Params2.52B
Context128K
Best fitF16 5.9 GB
QW
Qwen3 4B
Qwen · enacimie
Params4.02B
Context40K
Best fitQ4_K_M 6.7 GB
HO
Sakura K2 Horizon 7B
Horizon · webmp3
Params9B
Context512K
Smallest3.8 GB
MI
MixTaoTruthful-13B-slerp
Mixtaotruthful · mradermacher
Params12.9B
Context32K
Best fitQ3_K_M 7.8 GB
ST
Starcoder2 15b
StarCoder · mradermacher
Params16B
Context16K
Best fitIQ3_XS 7.9 GB
DE
Qwen2.5 MOE 2X1.5B DeepSeek Uncensored Censored 4B
DeepSeek · DavidAU
Params4.1B
Context128K
Best fitQ8_0 5.1 GB
LL
Meta Llama 3 8B Instruct GGUF Imatrix smashed
Llama · PrunaAI
Params8B
Context8K
Best fitQ5_1 7.6 GB
QW
dnotitia_Smoothie Qwen3 4B
Qwen · Alcoft
Params4B
Context40K
Best fitQ8_K_XL 6.4 GB
SA
Saiga_Yandexgpt_8B_Sft_M4_D19_Hf
Saiga · IlyaGusev
Params8B
Context32K
Best fitQ5_K_M 7.3 GB
BO
Borealis Open 12b
Borealis · mradermacher
Params11.8B
Context128K
Best fitIQ2_M 8.0 GB
LF
LFM2.5 8B A1B Hermes Agentic Coder Abliterated v3
Lfm · mradermacher
Params8.47B
Context125K
Best fitQ5_K_S 8.0 GB
LU
Lumimaid Magnum v4 12B
Lumimaid · bartowski
Params12.2B
Context128K
Best fitQ3_K_M 7.9 GB
QW
DPO Trained Qwen2.5 Python Coder 7B
Qwen · mradermacher
Params7.62B
Context32K
Best fitQ6_K 7.2 GB
CH
Chaotic Order 24B V5
Chaotic · mradermacher
Params23.6B
Context128K
Best fitIQ1_M 7.6 GB
QW
Qwen3.5 2B Uncensored Zero Refusal SOMA
Qwen · mradermacher
Params1.88B
Context256K
Best fitQ6_K 2.5 GB
QW
Qwen3 Coder Next Uncensored Heretic
Qwen · mradermacher
Params79.7B
Context256K
Q4_K_M48.5 GB
MI
Tamil-Mistral-7B-v0.1
Mistral · RichardErkhov
Params7.39B
Context32K
Best fitQ6_K 7.6 GB
YU
Ruach Studio Models v2
Yue · goldhub
Params632M
Context32K
Best fitQ4_0 7.6 GB
CO
Yi Coder 1.5B
Coder · lmstudio-community
Params1.48B
Context128K
Best fitQ8_0 3.7 GB
NE
Nemotron 3.5 Embed 8B BF16
Nemotron · W4D
Params7.95B
Context256K
Best fitQ5_1 7.7 GB
RE
REBEL-OpenChat-3.5
Rebel · mradermacher
Params7.24B
Context8K
Best fitQ6_K 7.5 GB
MI
Sakura MiniCPM V 4.7 1B Uncensored
MiniCPM · webmp3
Params1.01B
Context256K
Best fitQ8_0 2.0 GB
MU
Muse Glimmer 30B AZ Focus
Muse · mradermacher
Params27.9B
Context128K
Best fitIQ1_M 8.0 GB
QW
Qwen2.5 Coder 7B Instruct Abliterated
Qwen · mradermacher
Params7.62B
Context32K
Best fitQ6_K 7.2 GB
QW
Qwen3 14B NSFW FDA
Qwen · mradermacher
Params14.8B
Context32K
Best fitIQ3_XXS 7.8 GB
QW
Qwen3 1.7B
Qwen · rippertnt
Params2.03B
Context40K
Best fitQ4_K_M 2.7 GB
LL
ultravox v0 5 llama 3 1 8b
Llama · ggml-org
Params8B
Context128K
Best fitQ4_K_M 6.5 GB
GP
SpaceQA Gpt Oss 20b
gpt-oss · mradermacher
Params20.9B
Context128K
Q4_K_M15.8 GB