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.
GR
granite 20b code instruct i1
Granite · mradermacher
Params20B
Context8K
Best fitIQ2_M 7.8 GB
GU
GUI Owl 1.5 2B Instruct
Gui · mradermacher
Params1.72B
Context32K
Best fitF16 4.9 GB
MP
Mpt 7b Storywriter
Mpt · mradermacher
Params6.65B
Context64K
Best fitIQ3_XS 7.7 GB
LL
Hermes 3 Llama 3.1 8B Lorablated
Llama · mlabonne
Params8B
Context128K
Best fitQ5_K_M 7.3 GB
CO
codegeex4-all-9b
Codegeex · legraphista
Params9.4B
Context128K
Best fitQ5_K 8.0 GB
QW
Qwen Image 2.1 Text Encoder Heretic DHQ
Qwen · pottokao
Params8.2B
Context256K
Best fitQ4_K_M 6.7 GB
QW
Qwen3 1.7B Abliterated
Qwen · bartowski
Params1.72B
Context40K
Best fitBF16 4.9 GB
PA
PaddleOCR-VL-1.6
Paddleocr · Mungert
Params467M
Context128K
Best fitBF16 1.6 GB
NE
neutts air q4
Neutts · neuphonic
Params748M
Context—
Best fitQ4_0 1.1 GB
PA
Pantheon Reasoning 27B
Pantheon · bartowski
Params27.3B
Context256K
Q4_K_M18.0 GB
QW
EUAIAct Qwen2.5 0.5B Edge
Qwen · sallani
Params494M
Context32K
Best fitQ4_K_M 1.0 GB
IN
InternVL3 1B Instruct
Internvl · ggml-org
Params630M
Context32K
Best fitF16 1.9 GB
ST
L3 8B Stheno v3.2
Stheno · QuantFactory
Params8B
Context8K
Best fitQ5_1 7.6 GB
QW
Qwen2.5 1.5B Instruct
Qwen · lmstudio-community
Params1.54B
Context32K
Best fitQ8_0 2.4 GB
JA
Jan nano
Jan · Menlo
Params4B
Context40K
Best fitQ8_0 6.0 GB
XY
Xyntetik Kvist 14B
Xyntetik · mradermacher
Params14.4B
Context128K
Q4_K_M10.3 GB
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 6.4 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 fitIQ3_M 7.9 GB
MI
nondzu_mistral-7b-instruct-v0.2-code-ft
Mistral · TheBloke
Params7.24B
Context32K
Best fitQ6_K 7.5 GB
GE
Vikhr-Gemma-2B-instruct
Gemma · Vikhrmodels
Params2.61B
Context8K
Best fitBF16 6.6 GB
FI
SUFE AIFLM Lab Fin R1
Fin · bartowski
Params7.6B
Context32K
Best fitQ6_K_L 7.5 GB
QW
Qwen3 Uncensored TextEncoders Klein Z Image Anima
Qwen · LuffyTheFox
Params596M
Context40K
Smallest1.2 GB
TE
Terminal RSI 27B
Terminal · bartowski
Params27.3B
Context256K
Q4_K_M17.4 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 6.2 GB
QW
Replete LLM V2.5 Qwen 14b
Qwen · bartowski
Params14.8B
Context32K
Best fitQ2_K 7.9 GB