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.
FL
vllm-d3-flash
Flash · ggml-org
Params8.95B
Context256K
Best fitBF16 19.5 GB
QW
Qwen3.8 9B Distill uncensored heretic Q4 K M
Qwen · ge525
Params9.2B
Context256K
Best fitQ4_K_M 7.4 GB
GE
Gemma 3 12b It
Gemma · bartowski
Params11.8B
Context128K
Best fitQ8_0 16.2 GB
FL
RecursiveSI flint
Flint · bartowski
Params39.8B
Context256K
Best fitIQ4_XS 23.8 GB
LF
LFM2 VL 1.6B
Lfm · LiquidAI
Params1.17B
Context125K
Best fitF16 3.9 GB
ST
L3-8B-Stheno-v3.2
Stheno · Lewdiculous
Params8B
Context8K
Best fitQ8_0 10.1 GB
LL
VAGOsolutions Llama 3 SauerkrautLM 70b Instruct
Llama · RichardErkhov
Params6B
Context—
Best fitQ3_K 13.1 GB
PA
PaddleOCR VL 1.5
Paddleocr · PaddlePaddle
Params467M
Context128K
Smallest0.9 GB
QW
Qwen3.5 9B Claude 4.6 Opus Reasoning Distilled
Qwen · Jackrong
Params8.95B
Context256K
Best fitQ8_0 11.1 GB
GE
gemma-2b-it
Gemma · lmstudio-ai
Params2.51B
Context8K
Best fitQ8_0 3.3 GB
QW
Atomic Chat / Qwen3.5 9B
Qwen · AtomicChat
Params8.95B
Context256K
Best fitQ8_0 11.1 GB
QW
Qwen3.8
Qwen · cHunter789
Params27B
Context256K
Smallest14.8 GB
MI
Mistral Nemo 2407 12B Thinking Claude Gemini GPT5.2 Uncensored HERETIC
Mistral · mradermacher
Params12.2B
Context1000K
Best fitQ8_0 14.9 GB
LF
LFM2.5 230M LocalAI
Lfm · weareapexcreators
Params230M
Context125K
Best fitQ8_0 1.2 GB
JI
jina reranker v1 tiny en
Jina · mradermacher
Params33M
Context8K
Best fitQ2_K 0.6 GB
MI
Mistral Small 4 119B 2603
Mistral · bartowski
Params119B
Context1024K
Q4_K_M72.6 GB
MA
magnum v4 12b
Magnum · bartowski
Params12.2B
Context1000K
Best fitQ8_0 14.9 GB
MI
Mistral Small Instruct 2409
Mistral · mradermacher
Params22.2B
Context128K
Best fitQ6_K 20.6 GB
QW
Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled
Qwen · mradermacher
Params27B
Context256K
Best fitQ5_K_M 22.0 GB
SP
Spark X2.6 4B
Spark · bartowski
Params4.11B
Context1024K
Best fitBF16 9.9 GB
QW
Qwen3.5-2B
Qwen · weareapexcreators
Params1.94B
Context256K
Best fitQ5_K_M 2.4 GB
ST
StartLux-Decision-v1.1-9B-AutoThink
Startlux · startlux-models
Params8.95B
Context256K
Best fitQ8_0 11.1 GB
LL
Llama 3.2 3B Instruct abliterated
Llama · QuantFactory
Params3.2B
Context128K
Best fitQ8_0 4.9 GB
QW
Qwen3.8 27B Uncensored
Qwen · mradermacher
Params27.3B
Context256K
Best fitQ5_K_M 22.2 GB
QW
Qwen3.5 2B Claude 4.6 Opus Reasoning Distilled
Qwen · Jackrong
Params1.88B
Context256K
Best fitQ8_0 2.9 GB
GE
gemma 4 E4B it uncensored
Gemma · TrevorJS
Params7.5B
Context128K
Best fitQ8_0 9.9 GB
MI
MiniCPM5 2B LocalAI
MiniCPM · weareapexcreators
Params2.52B
Context128K
Best fitQ8_0 3.5 GB
NA
Nanbeige4.2 3B
Nanbeige · bartowski
Params4.17B
Context256K
Best fitBF16 9.6 GB
ST
StartLux Decision v1 9B Q8 0
Startlux · startlux-models
Params8.95B
Context256K
Best fitQ8_0 11.1 GB
WI
ehartford_wizardlm-7b-uncensored
Wizardlm · TheBloke
Params6.74B
Context2K
Best fitQ8_0 12.0 GB