GGUF models that fit in 16 GB
182247 GGUF language models have at least one quant whose estimated memory use is 16 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
Qwen2.5 14B Instruct
Qwen · ThomasBaruzier
Params14.8B
Context32K
Best fitQ6_K 14.2 GB
LL
Llama 3.1 SauerkrautLM 8b Instruct
Llama · bartowski
Params8B
Context128K
Best fitQ8_0 10.1 GB
YI
CursorCore Yi 9B i1
Yi · mradermacher
Params8.83B
Context128K
Best fitQ6_K 8.6 GB
GR
Grug 27b
Grug · bartowski
Params27B
Context256K
Best fitIQ3_XS 15.7 GB
OL
OLMo 7B 0424 Hf
OLMo · mradermacher
Params6.89B
Context4K
Best fitQ6_K 10.4 GB
GR
Granite 3b Code Instruct
Granite · RichardErkhov
Params3.48B
Context2K
Best fitQ8_0 6.9 GB
OR
Ornith 1.5 9B Uncensored
Ornith · mradermacher
Params8.95B
Context256K
Best fitQ6_K 8.9 GB
LF
LFM2.5 24B A2B Uncensored2
Lfm · mradermacher
Params24B
Context128K
Best fitIQ4_XS 16.0 GB
QW
Qwen3.5 9B Uncensored HauhauCS Aggressive MTP GGUF NVFP4
Qwen · AIconjured
Params456M
Context256K
Smallest6.3 GB
LL
Colossal LLaMA 2 13b Base
Llama · mradermacher
Params13.4B
Context4K
Best fitQ4_K_M 15.3 GB
MI
Mahou-1.3c-mistral-7B
Mistral · mradermacher
Params7.24B
Context32K
Best fitQ6_K 7.5 GB
NE
Nemotron Cascade 8B Thinking
Nemotron · bartowski
Params8.19B
Context32K
Best fitQ8_0 10.4 GB
QW
Qwen2-1.5B
Qwen · legraphista
Params1.54B
Context128K
Best fitBF16 3.8 GB
D3
d3
mradermacher
Params27B
Context256K
Best fitQ3_K_M 15.9 GB
SA
Sage A1.5 Heretic Abliterated Uncensored
Sage · mradermacher
Params34.7B
Context256K
Best fitQ2_K 14.1 GB
BO
prism ml Bonsai 8B unpacked
Bonsai · bartowski
Params8.19B
Context64K
Best fitQ8_0 10.4 GB
DI
Dirty Muse Writer v01 Uncensored Erotica NSFW
Dirty · mradermacher
Params9.24B
Context8K
Best fitQ8_0 13.1 GB
LL
Llama 2 Coder 7B
Llama · TheBloke
Params6.74B
Context4K
Best fitQ8_0 12.0 GB
LL
Llama 3.2 1b Abliterated
Llama · mradermacher
Params1.24B
Context128K
Best fitQ6_K 1.8 GB
LL
Reflection Llama 3.1 8B i1
Llama · mradermacher
Params8B
Context128K
Best fitQ6_K 8.2 GB
QW
Qwen3 8B Uncensor v2
Qwen · mradermacher
Params8.19B
Context40K
Best fitQ8_0 10.4 GB
LY
LYNX ALPHA
Lynx · mradermacher
Params8.95B
Context256K
Best fitQ6_K 9.0 GB
LF
Lfm2.5 2.6b Fable5 Coding Agent Heretic
Lfm · mradermacher
Params2.7B
Context128K
Best fitQ6_K 4.7 GB
VN
Vnpen Writer 9b v1.0
Vnpen · mradermacher
Params8.95B
Context256K
Best fitQ6_K 9.0 GB
QW
Qwen2.5 32B ArliAI RPMax v1.3
Qwen · bartowski
Params32.8B
Context32K
Best fitQ2_K_L 15.7 GB
DE
Deepseek Coder 6.7b Instruct
DeepSeek · mradermacher
Params6.74B
Context16K
Best fitQ6_K 10.3 GB
DE
DeepSeek R1 Distill Qwen 7B Abliterated v2
DeepSeek · mradermacher
Params7.62B
Context128K
Best fitQ8_0 9.1 GB
LL
Llama Guard 3 8B
Llama · legraphista
Params8B
Context128K
Best fitQ8_0 10.1 GB
QW
Qwen2.5 14B
Qwen · bartowski
Params14.8B
Context128K
Best fitQ6_K_L 14.6 GB
QW
Qwen3 14B
Qwen · mradermacher
Params14.8B
Context40K
Best fitQ6_K 14.0 GB