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.
LF
LFM2.5 24B A2B Uncensored
Lfm · AtomicChat
Params24B
Context128K
Best fitQ5_K_M 20.5 GB
QW
Qwen2.5 Coder 14B Instruct AWQ
Qwen · Qwen
Params29B
Context128K
Best fitQ5_K_M 23.1 GB
QW
Qwen3Vl 2b Instruct
Qwen · Qwen
Params1.72B
Context256K
Best fitF16 4.9 GB
SP
Spark X2.6 4B
Spark · XHToken
Params4.45B
Context1024K
Q4_K_M3.5 GB
AG
Agents A1 4B
Agents · InternScience
Params4.21B
Context256K
Best fitQ4_K_M 4.3 GB
GE
gemma 4 E2B it qat q4 0
Gemma · google
Params4.63B
Context128K
Best fitQ4_0 4.4 GB
QW
Qwen3.8 27B Uncensored
Qwen · azukivc
Params27.3B
Context256K
Best fitQ5_K_M 22.2 GB
QW
Qwen3.6 35B A3B
Qwen · bartowski
Params35.5B
Context256K
Best fitQ4_K_L 23.9 GB
LL
Llama 3.2 3B Instruct
Llama · bartowski
Params3.21B
Context128K
Best fitF16 7.9 GB
LA
Laguna S 2.1 APEX
Laguna · Myric
Params118B
Context1024K
Best fitQ8_0 1.9 GB
GE
gemma 4 26B A4B it qat
Gemma · unsloth
Params430M
Context128K
Best fitQ4_K_XL 15.8 GB
QW
Qwen3 1.7B Instruct
Qwen · Qwen
Params1.72B
Context40K
Best fitQ8_0 3.3 GB
LF
LFM2.5-24B-A2B-Preview
Lfm · unsloth
Params24B
Context128K
Best fitQ5_K_XL 21.1 GB
QW
Qwen3.5-27B
Qwen · unsloth
Params27B
Context256K
Best fitQ5_K_XL 22.8 GB
GR
Parable Granite 4.1 3B Claude Fable 5
Granite · AnkitAI
Params3.4B
Context128K
Best fitF16 8.0 GB
LL
Llama-3.2-3B-Instruct
Llama · unsloth
Params3.21B
Context128K
Best fitF16 7.9 GB
GR
Parable Granite 4.1 8B Claude Fable 5
Granite · AnkitAI
Params8.38B
Context128K
Best fitF16 18.6 GB
QW
Qwen3.8 Flash Next Uncensored i1
Qwen · mradermacher
Params177B
Context—
Smallest0.6 GB
GE
gemma-4-E2B-it
Gemma · ggml-org
Params4.65B
Context128K
Best fitBF16 9.9 GB
QW
Qwen_Qwen3.5 4B
Qwen · lmstudio-community
Params4.21B
Context256K
Best fitQ8_0 6.1 GB
QW
Qwen2.5 14B Instruct
Qwen · bartowski
Params14.8B
Context32K
Best fitQ8_0 17.8 GB
BG
bge-small-en-v1.5
BGE · CompendiumLabs
Params33M
Context512
Best fitF32 0.8 GB
QW
Holo 3.1 35B A3B
Qwen · Hcompany
Params34.7B
Context256K
Best fitQ4_K_M 22.5 GB
TE
Ternary Bonsai 2 27B Uncensored Heretic
Ternary · OS-Software
Params27B
Context256K
Smallest5.9 GB
QW
Qwen3 Embedding 0.6b
Qwen · Qwen
Params596M
Context32K
Best fitF16 2.6 GB
HO
Diplodocus preview 4
Horizon · OsaurusAI
Params9B
Context512K
Best fitQ8_0 11.3 GB
QW
Qwen_Qwen3.6 35B A3B
Qwen · lmstudio-community
Params34.7B
Context256K
Best fitQ4_K_M 22.3 GB
QW
Qwopus3.6 27B Coder Compat MTP
Qwopus · Jackrong
Params27B
Context256K
Best fitQ5_K_M 22.2 GB
DE
Deepseek-R1-0528-Qwen3-8B
DeepSeek · unsloth
Params8.19B
Context128K
Best fitBF16 18.1 GB
QW
Qwen3.8 27B Uncensored
Qwen · bartowski
Params27.3B
Context256K
Best fitQ5_K_M 23.4 GB