GGUF models that fit in 24 GB
193369 GGUF language models have at least one quant whose estimated memory use is 24 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.
SA
Sabi Noema
Sabi · mradermacher
Params27B
Context256K
Best fitQ5_K_M 21.9 GB
OL
OLMo 2 1124 13B Instruct
OLMo · bartowski
Params13.7B
Context4K
Best fitQ8_0 21.8 GB
QW
JonathanColetti Qwen3.8 27B Uncensored
Qwen · mradermacher
Params27.3B
Context256K
Best fitQ5_K_M 22.2 GB
QW
Qwen2 VL 7B Instruct
Qwen · bartowski
Params7.62B
Context32K
Best fitF16 16.2 GB
QW
Qwen2 Audio 7B Instruct
Qwen · mradermacher
Params7.75B
Context8K
Best fitF16 20.3 GB
ER
Ernie-4.5-21B-A3B-Pt
Ernie · unsloth
Params21.8B
Context128K
Best fitQ6_K_XL 20.2 GB
PH
Phi 3.1 mini 4k instruct
Phi · bartowski
Params3.82B
Context4K
Best fitF32 19.0 GB
GL
GLM 4.7 Flash Derestricted
GLM · mradermacher
Params30B
Context198K
Best fitQ5_K_M 22.6 GB
HE
HERO 35B A3B
Hero · mradermacher
Params34.7B
Context256K
Best fitQ4_1 23.0 GB
IN
Intern Decision 4B
InternLM · bombdefuser-124
Params4.21B
Context256K
Smallest4.5 GB
DA
DanTagGen delta
Dantaggen · KBlueLeaf
Params393M
Context2K
Best fitF16 2.1 GB
MI
MiniCPM V Apps
MiniCPM · tc-mb
Params912M
Context256K
Best fitF16 4.2 GB
ID
ideogram 4
Ideogram · rectangleworm
Params8.19B
Context256K
Best fitQ8_0 11.8 GB
LL
Huihui Mistral Small 3.2 24B Instruct 2506 Abliterated Llamacppfixed
Llama · mradermacher
Params23.6B
Context128K
Best fitQ6_K 21.2 GB
MI
Mistral-Small-3.1-24B-Instruct-2503
Mistral · unsloth
Params23.6B
Context128K
Best fitQ6_K_XL 22.6 GB
QW
DEV ThinkingCap Qwen3.8 27B
Qwen · ngquocvinh
Params27.3B
Context256K
Best fitQ5_K_M 22.2 GB
RO
Rocinante X 12B v1 Heretic Uncensored
Rocinante · mradermacher
Params12.2B
Context128K
Best fitQ8_0 14.9 GB
SE
Seed-Oss-36B-Instruct
Seed · unsloth
Params36.2B
Context512K
Best fitQ4_0 23.3 GB
TE
TerminalHorizon 35B A3B
Terminalhorizon · mradermacher
Params34.7B
Context256K
Best fitQ4_1 23.0 GB
OL
OLMoE 1B 7B 0924 Instruct
OLMo · bartowski
Params6.9B
Context4K
Best fitF16 15.4 GB
GR
Granite Vision 4.1 4b
Granite · ibm-granite
Params3.4B
Context128K
Best fitBF16 8.0 GB
CA
Carbon-X
Carbon · HuggingFaceBio
Params14.8B
Context40K
Best fitQ8_0 17.6 GB
FA
Fara1.5 4B
Fara · bartowski
Params4.21B
Context256K
Best fitBF16 10.0 GB
GE
BgGPT Gemma 3 27B IT
Gemma · INSAIT-Institute
Params27B
Context128K
Best fitQ5_K_M 23.9 GB
ME
Medgemma-27B-Text-It
Medgemma · unsloth
Params27B
Context128K
Best fitQ5_K_XL 24.0 GB
QW
Qwen3.8 Flash Next Abliterated Uncensored Turbo Brilliance 50x Reasoning Instruct GSQ RCO DFlash
Qwen · hotocooo
Params1.34B
Context256K
Best fitF32 3.8 GB
NE
Nemotron Cascade 2 30B A3B
Nemotron · bartowski
Params31.6B
Context1024K
Q4_K_M24.7 GB
QW
Qwen3.8 Flash Next MTP
Qwen · drluoto
Params3.9B
Context256K
Best fitBF16 9.1 GB
QW
Qwen3 8B Heretic
Qwen · saidutta69
Params8.19B
Context40K
Best fitF16 18.1 GB
CO
Yi Coder 9B Chat
Coder · RichardErkhov
Params8.83B
Context128K
Best fitQ8_0 10.7 GB