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.
PH
Phi 3.5 Mini Instruct
Phi · bartowski
Params3.82B
Context128K
Best fitF32 19.0 GB
OR
OrcaCyber Nano 1.0
Orcacyber · orcarouter
Params1.92B
Context256K
Smallest2.1 GB
LL
Dolphin 3.0 Llama 3.1 8B
Llama · bartowski
Params8B
Context128K
Best fitF16 17.6 GB
ME
Medgemma-4B-It
Medgemma · unsloth
Params3.88B
Context128K
Best fitBF16 9.4 GB
RA
Raon 1 Mini Preview
Raon · KRAFTON
Params28.8B
Context256K
Best fitQ8_0 19.1 GB
QW
Qwen3 14B Abliterated
Qwen · bartowski
Params14.8B
Context40K
Best fitQ8_0 17.5 GB
GE
Gemma 4 26B A4B It Uncensored Heretic
Gemma · llmfan46
Params25.2B
Context256K
Best fitQ4_K_S 24.0 GB
QW
Qwen3-Next-80B-A3B-Thinking
Qwen · unsloth
Params80B
Context256K
Best fitIQ1_S 24.0 GB
CY
z image cyberrealistic v9
Cyberrealistic · gimly13
Params6.15B
Context40K
Best fitQ8_0 9.0 GB
TI
py007_tinyllama-1.1b-chat-v0.3
Tinyllama · TheBloke
Params1.1B
Context2K
Best fitQ8_0 1.9 GB
QW
Bonsai 2 27B Ternary CRACK
Qwen · dealignai
Params27B
Context256K
Smallest7.2 GB
FL
FLUX.2 klein 9B
Flux · leejet
Params9.08B
Context—
Best fitQ8_0 11.7 GB
QW
Qwen2.5-VL-3B-Instruct
Qwen · Mungert
Params3.1B
Context125K
Best fitBF16 7.0 GB
GL
GLM 4.7 Flash Uncensored Heretic NEO CODE Imatrix MAX
GLM · DavidAU
Params29.9B
Context198K
Best fitQ5_K_M 23.0 GB
EM
Embeddinggemma 300m Qat Q8_0 Unquantized
Embeddinggemma · ggml-org
Params303M
Context2K
Best fitQ8_0 1.0 GB
QW
Qwen3VL 8B Uncensored HauhauCS Aggressive
Qwen · HauhauCS
Params8.2B
Context256K
Best fitBF16 18.1 GB
GE
Gemma 2 2b It
Gemma · bartowski
Params2.61B
Context8K
Best fitF32 11.8 GB
QW
Qwen2.5 Coder 7B Instruct
Qwen · lmstudio-community
Params7.62B
Context32K
Best fitQ8_0 9.1 GB
QW
Qwen2.5 Coder 0.5B Instruct AWQ
Qwen · Qwen
Params630M
Context32K
Q4_K_M0.5 GB
QW
Qwen2.5 7B Instruct Abliterated
Qwen · mradermacher
Params7.62B
Context32K
Best fitF16 16.2 GB
GE
Huihui gemma 4 26B A4B it qat q4 0 unquantized abliterated
Gemma · huihui-ai
Params25.2B
Context128K
Best fitQ4_0 18.4 GB
TE
TerminalHorizon 122B A10B
Terminalhorizon · mradermacher
Params122B
Context256K
Q4_K_M74.2 GB
LF
LFM2.5-VL-3B
Lfm · LiquidAI
Params2.7B
Context32K
Best fitBF16 7.9 GB
PR
Fish Speech S2 Pro Dual AR
Pro · rodrigomt
Params4.95B
Context32K
Best fitF16 11.2 GB
DE
DeepSeek R1 Distill Qwen 14B
DeepSeek · lmstudio-community
Params14.8B
Context128K
Best fitQ8_0 17.8 GB
LL
tiny llamas
Llama · ggml-org
Params24M
Context—
Smallest0.0 GB
HO
K2 Horizon 7B
Horizon · IFM
Params9B
Context512K
Best fitBF16 19.7 GB
QW
Huihui Qwen3 Coder 30B A3B Instruct Abliterated
Qwen · Thaurock
Params30.5B
Context256K
Best fitQ5_K_M 23.0 GB
QW
Qwen2.5 7B Instruct abliterated v2
Qwen · QuantFactory
Params7.6B
Context32K
Best fitQ8_0 9.1 GB
DE
DeepSeek R1 Distill Qwen 32B
DeepSeek · unsloth
Params32.8B
Context128K
Best fitQ4_K_M 22.5 GB