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.
TI
Tini Cybersec 8B A1B
Tini · bartowski
Params8.47B
Context125K
Best fitBF16 19.1 GB
GR
Granite 4.0 H Small
Granite · ibm-granite
Params32.2B
Context1024K
Best fitQ3_K_L 22.3 GB
HO
K2-Horizon-7B
Horizon · bartowski
Params9B
Context512K
Best fitBF16 19.7 GB
VE
Veloxy Titan 32B
Veloxy · mradermacher
Params26.9B
Context256K
Best fitQ5_K_M 21.9 GB
LF
LFM2.5-24B-A2B
Lfm · OS-Software
Params24B
Context128K
Best fitQ6_K 22.9 GB
SP
Spark X2.5 4B
Spark · ngquocvinh
Params4.1B
Context1024K
Best fitQ8_0 6.1 GB
MI
Mistral 7B v0.1
Mistral · MaziyarPanahi
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
QW
Qwen2.5 Coder 3B
Qwen · bartowski
Params3.09B
Context32K
Best fitF16 7.0 GB
KO
Kolibri 1
Kolibri · bartowski
Params78.1B
Context256K
Best fitIQ1_M 21.1 GB
GE
Gemma 4 26B A4B It Abliterated
Gemma · mradermacher
Params25.2B
Context256K
Best fitQ4_K_S 24.0 GB
ME
G4 MeroMero 26B A4B
Meromero · zerofata
Params25.2B
Context256K
Best fitIQ4_XS 22.5 GB
LL
dolphin-llama3-zh-cn-uncensored
Llama · stephenlzc
Params8B
Context8K
Best fitBF16 17.6 GB
JI
JiRackUltra_32b
Jirackultra · CMSManhattan
Params32.8B
Context128K
Best fitQ4_K_M 22.5 GB
PY
Pyrex 8B Instruct Uncensored i1
Pyrex · mradermacher
Params7.62B
Context32K
Best fitQ6_K 7.2 GB
GE
Huihui Gemma 4 12B It Abliterated
Gemma · mradermacher
Params11.9B
Context128K
Best fitQ6_K 23.2 GB
CO
CohereForAI aya 23 35B
Cohereforai · RichardErkhov
Params35B
Context—
Best fitIQ3_M 19.2 GB
GR
Granite 3.3 2b Instruct
Granite · ibm-granite
Params2.53B
Context128K
Best fitF16 6.2 GB
PH
phonon 40m pt
Phonon · gradium
Params51M
Context—
Smallest0.1 GB
GU
GUI Owl 1.5 4B Instruct
Gui · mradermacher
Params4B
Context32K
Best fitF16 9.8 GB
AS
Asmodeus 24B v3
Asmodeus · mradermacher
Params23.6B
Context128K
Best fitQ6_K 21.2 GB
QW
Qwen3.8 35B A3B Distill
Qwen · mradermacher
Params35.5B
Context256K
Best fitQ4_1 23.6 GB
OR
Ornith-1.5-35B
Ornith · na0x2c6
Params35.5B
Context256K
Best fitQ4_K_M 23.6 GB
GD
GDP 4B
Gdp · mradermacher
Params4.02B
Context256K
Best fitF16 9.8 GB
QW
Qwen3.8 27B
Qwen · ArtomYuan
Params27.3B
Context256K
Best fitQ4_0 17.7 GB
LL
Llm Jp 4.1 32b A3B Thinking
Llm · OS-Software
Params32B
Context64K
Best fitQ4_K_M 22.6 GB
DE
DeepSeek R1 Distill Qwen 7B
DeepSeek · mradermacher
Params7.62B
Context128K
Best fitF16 16.2 GB
HO
K2 Horizon 32B Heretic
Horizon · mradermacher
Params34.8B
Context512K
Best fitQ4_K_M 23.7 GB
YI
ChatAllInOne-Yi-34B-200K-V1
Yi · mradermacher
Params34.4B
Context195K
Best fitQ4_K_M 23.2 GB
QW
Qwen3.8 Flash Next FP8 Abliterated
Qwen · GCSA-AiLab
Params177B
Context256K
Best fitQ8_0 5.5 GB
GE
gemma-1.1-7b-it
Gemma · bartowski
Params8.54B
Context8K
Best fitQ8_0 13.3 GB