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.
HO
K2-Horizon-3.7B
Horizon · mradermacher
Params5.06B
Context512K
Best fitQ6_K 5.9 GB
HU
Hunyuan 0.5B Instruct
Hunyuan · bartowski
Params539M
Context256K
Best fitBF16 2.4 GB
GR
Granite 3.1 2b Instruct
Granite · bartowski
Params2.53B
Context128K
Best fitF16 6.2 GB
QW
Qwen3-4B-abliterated
Qwen · Mungert
Params4B
Context40K
Best fitBF16 9.8 GB
YI
dolphin-2.9.3-Yi-1.5-34B-32k
Yi · mradermacher
Params34.4B
Context32K
Best fitIQ3_XXS 15.8 GB
OM
Omega Arsenal 12B
Omega · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
PY
Pythia 410m
Pythia · mradermacher
Params405M
Context2K
Best fitQ4_0 1.6 GB
LL
Llama 7B rollercoaster v2 i1
Llama · mradermacher
Params6.74B
Context4K
Best fitQ6_K 10.3 GB
MI
nondzu_mistral-7b-instruct-v0.2-code-ft
Mistral · TheBloke
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
GE
Vikhr-Gemma-2B-instruct
Gemma · Vikhrmodels
Params2.61B
Context8K
Best fitF32 11.8 GB
FI
SUFE AIFLM Lab Fin R1
Fin · bartowski
Params7.6B
Context32K
Best fitQ8_0 9.1 GB
QW
Qwen3.5 35B A3B Claude Distilled APEX
Qwen · mudler
Params34.7B
Context256K
Smallest14.3 GB
QW
Qwen3 Uncensored TextEncoders Klein Z Image Anima
Qwen · LuffyTheFox
Params596M
Context40K
Best fitQ8_0 10.1 GB
TE
Terminal RSI 27B
Terminal · bartowski
Params27.3B
Context256K
Best fitIQ3_XS 15.5 GB
QW
Qwen3.6 27B A3B CoderX
Qwen · ManniX-ITA
Params26.2B
Context256K
Best fitIQ4_XS 15.4 GB
LI
LightOnOCR 3 0.8B
Lightonocr · NANI-Nithin
Params752M
Context256K
Best fitBF16 2.4 GB
PH
phi-4-mini-instruct
Phi · Mungert
Params3.84B
Context128K
Best fitBF16 9.3 GB
QW
Replete LLM V2.5 Qwen 14b
Qwen · bartowski
Params14.8B
Context32K
Best fitQ6_K_L 14.6 GB
QW
Qwen3.5 9B The Bradbury F451 Pro Writer Uncensored Heretic
Qwen · mradermacher
Params8.95B
Context256K
Best fitQ8_0 11.1 GB
QW
Qwen3.5 9B C3SM SDM Agentic Coder
Qwen · OliviaRossi
Params8.95B
Context256K
Best fitQ5_K_M 8.0 GB
QW
Qwen2.5 14B
Qwen · mradermacher
Params14.8B
Context128K
Best fitQ6_K 14.2 GB
IN
Ingot X 27B Q2
Ingot · dendriteholdings
Params26.9B
Context256K
Smallest7.2 GB
WI
Wicked Stuff 26B A4B v2.1 FINAL
Wicked · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
YI
Yi 1.5 34B
Yi · RichardErkhov
Params34.4B
Context4K
Best fitQ2_K 15.3 GB
QW
Qwen3 VL 8B Instruct Abliterated v2
Qwen · qign
Params8.19B
Context256K
Best fitQ8_0 10.4 GB
HO
Holo 3.1 4B
Holo · prithivMLmods
Params4.84B
Context256K
Best fitBF16 11.3 GB
SE
SexyGPT v3 Thinking Female
Sexygpt · mradermacher
Params27.3B
Context256K
Best fitIQ3_M 15.4 GB
MT
Mtreelva Dune 12B
Mtreelva · mradermacher
Params12.9B
Context256K
Q4_K_M7.9 GB
OU
OuteTTS 0.2 500M
Outetts · OuteAI
Params500M
Context32K
Q4_K_M0.4 GB
SA
SaulLM 54B Instruct i1
Saullm · mradermacher
Params46.7B
Context32K
Best fitIQ2_S 15.7 GB