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.
QW
speakoflow mini
Qwen · SpeakoFlow
Params773M
Context256K
Best fitBF16 2.5 GB
QW
Qwen2.5-Omni-7B
Qwen · unsloth
Params7.62B
Context32K
Best fitBF16 16.2 GB
BA
Bamboo 1 LocalAI
Bamboo · weareapexcreators
Params11.9B
Context256K
Best fitQ4_K_M 20.8 GB
HE
Hemmingway 1 Heretic MTP V3 Final
Hemmingway · brainnxdomain
Params27.3B
Context256K
Best fitQ5_K_M 22.2 GB
OR
Ornith 1.0 9B MTP LocalAI
Ornith · weareapexcreators
Params9.2B
Context256K
Best fitQ4_K_M 7.4 GB
MI
vllm-d3-mini
Mini · ggml-org
Params4.84B
Context256K
Best fitBF16 11.3 GB
QW
Qwen2.5 3B Instruct Abliterated
Qwen · mradermacher
Params3.4B
Context32K
Best fitF16 7.6 GB
QW
Qwen3-Coder-30B-A3B-Instruct
Qwen · ggml-org
Params30.5B
Context256K
Best fitQ4_K_M 19.3 GB
GE
Gemma 4 26B A4B StyleTune V2
Gemma · mradermacher
Params26B
Context256K
Best fitQ4_0 23.5 GB
LF
LFM2 24B A2B
Lfm · LiquidAI
Params23.8B
Context125K
Best fitQ6_K 22.8 GB
QW
Qwen3 VL 8B Instruct Abliterated v2.0
Qwen · mradermacher
Params8.19B
Context256K
Best fitF16 18.1 GB
QW
Qwen3.5 9B Claude 4.6 HighIQ INSTRUCT HERETIC UNCENSORED
Qwen · mradermacher
Params8.95B
Context256K
Best fitF16 19.5 GB
QW
Qwen3.8 27B Omnimerge v6
Qwen · ManniX-ITA
Params27.3B
Context256K
Best fitQ5_K_L 23.0 GB
QW
Qwen2.5 7B Instruct Abliterated v2
Qwen · mradermacher
Params7.62B
Context32K
Best fitF16 16.2 GB
QW
Mica v0.1 4B
Qwen · sky7350
Params4.84B
Context256K
Best fitBF16 11.3 GB
UN
Undi95 Emerhyst 20B
Undi · RichardErkhov
Params920M
Context—
Best fitQ2_K 8.8 GB
MI
Dolphin Mistral 24B Venice Edition
Mistral · douganger
Params23.6B
Context128K
Best fitQ6_K 21.2 GB
GE
Gemma 4 12B It Heretic
Gemma · igorls
Params11.9B
Context128K
Best fitQ4_K_M 20.8 GB
MI
Ministral-3-14B-Instruct-2512
Mistral · unsloth
Params13.5B
Context256K
Best fitQ8_K_XL 19.0 GB
BG
bge-small-zh-v1.5
BGE · CompendiumLabs
Params24M
Context512
Best fitF32 0.7 GB
QW
Qwen3.5-35B-A3B
Qwen · unsloth
Params35.5B
Context256K
Best fitQ4_K_XL 24.0 GB
QW
Ingot XIV 27B Q2
Qwen · dendriteholdings
Params26.9B
Context256K
Smallest5.9 GB
OP
opendecider small
Opendecider · manjunathshiva
Params4.02B
Context256K
Best fitQ8_0 6.0 GB
QW
LocalAI functioncall qwen2.5 7b v0.5 Q4 K M
Qwen · LocalAI-io
Params7.62B
Context32K
Best fitQ4_K_M 5.7 GB
TE
Tessera-27B-B-CJK
Tessera · ZelligeAI
Params27.3B
Context256K
Best fitQ5_K_XL 23.6 GB
GE
Gemory 26B A4B
Gemma · UltimateIntent
Params25.2B
Context256K
Best fitQ4_0 23.0 GB
JA
Jan-v2-VL-high
Jan · janhq
Params8.2B
Context256K
Q4_K_M5.0 GB
ME
Medgemma-1.5-4B-It
Medgemma · unsloth
Params3.88B
Context128K
Best fitBF16 9.4 GB
QW
Qwen_Qwen3.5 27B
Qwen · lmstudio-community
Params27B
Context256K
Best fitQ4_K_M 19.2 GB
NE
privacy-filter-nemotron
Nemotron · LocalAI-io
Params1.4B
Context128K
Best fitF16 3.4 GB