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.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen2.5 Coder 7B Instruct
Qwen · bartowski
Params7.62B
Context32K
Best fitF16 16.2 GB
Coding
QW
Models Qwen Qwen3 8B
Qwen · MaziyarPanahi
Params8.19B
Context40K
Q4_K_M5.0 GB
GGUF
QW
Huihui Qwen3 14B Abliterated v2
Qwen · mradermacher
Params14.8B
Context40K
Best fitQ8_0 17.5 GB
GGUF
TR
Translategemma 4b It
Translategemma · bullerwins
Params3.88B
Context128K
Best fitQ8_0 5.8 GB
Vision
ME
Hy Memory 30B A3B
Memory · rapatsky
Params30B
Context256K
Best fitQ5_K_M 22.7 GB
GGUF
GE
Gemma-3-12B-It
Gemma · unsloth
Params11.8B
Context128K
Best fitQ8_K_XL 18.1 GB
Vision
KI
kitten tts 2
Kitten · KittenML
Params1.73B
Context40K
Smallest1.0 GB
GGUF
QW
Qwen_Qwen3.5 35B A3B
Qwen · lmstudio-community
Params34.7B
Context256K
Best fitQ4_K_M 22.3 GB
Vision
LL
Llama 2 7B Chat
Llama · TheBloke
Params6.74B
Context4K
Best fitQ8_0 12.0 GB
GGUF
BG
bge m3
BGE · gpustack
Params567M
Context8K
Q4_K_M0.4 GB
Embedding
ST
L3-8B-Stheno-v3.2
Stheno · bartowski
Params8B
Context8K
Best fitQ8_0 10.1 GB
GGUF
QW
Qwen3.8-Flash-Next
Qwen · ggml-org
Params177B
Context256K
Best fitBF16 8.4 GB
Vision
QW
Qwen3.6-27B-Uncensored-HauhauCS-Aggressive
Qwen · HauhauCS
Params27B
Context256K
Best fitQ5_K 23.5 GB
Vision
ST
StartLux-Decision-v1.1-27B-AutoThink
Startlux · startlux-models
Params27B
Context256K
Best fitQ4_K_M 19.2 GB
ReasoningVision
LL
Meta Llama 3 8B Instruct
Llama · MaziyarPanahi
Params8B
Context8K
Q4_K_M4.9 GB
GGUF
QW
Huihui Qwen3 8B Abliterated v2
Qwen · mradermacher
Params8.19B
Context40K
Best fitF16 18.1 GB
GGUF
QW
Models Qwen Qwen3 30B A3B
Qwen · MaziyarPanahi
Params30.5B
Context40K
Best fitQ5_K_M 23.0 GB
GGUF
GE
Gemma 3 4b It
Gemma · lmstudio-community
Params3.88B
Context128K
Best fitQ8_0 5.8 GB
Vision
QW
Qwen3 Omni 30B A3B Instruct
Qwen · ggml-org
Params30.5B
Context64K
Best fitQ4_K_M 19.9 GB
Vision
QW
Models Qwen Qwen3 32B
Qwen · MaziyarPanahi
Params32.8B
Context40K
Best fitQ4_K_M 22.4 GB
GGUF
QW
Huihui Qwen3.6 27B Abliterated
Qwen · huihui-ai
Params27.3B
Context256K
Best fitQ5_K 22.2 GB
Vision
ST
stories15M MOE
Stories · ggml-org
Params8M
Context256
Smallest0.0 GB
GGUF
LL
Llama 3.3 70B Instruct
Llama · bartowski
Params70.6B
Context128K
Best fitIQ2_XXS 22.3 GB
GGUF
QW
Qwen3 Embedding 4B
Qwen · Qwen
Params4B
Context40K
Best fitF16 9.8 GB
Embedding
NE
NVIDIA Nemotron 3.5 Bolt 74B A9B
Nemotron · unsloth
Params74B
Context256K
Best fitIQ2_XXS 22.6 GB
Vision
FA
Jiqing tiny random falcon
Falcon · RichardErkhov
Params—
Context—
Best fitIQ3_M 0.5 GB
GGUF
QW
Qwen3.5 0.8B
Qwen · ggml-org
Params773M
Context256K
Best fitBF16 2.5 GB
Vision
HU
Cyber Tiel Coder 35B A3B
Huihui · peculiar-ragdoll
Params34.7B
Context256K
Best fitQ4_K_XL 23.5 GB
CodingReasoningTool use
FR
FrontTerrain-HARP-1B
Frontterrain · frontterrain
Params123M
Context512
Best fitF16 0.8 GB
Coding
QW
Qwen3-VL-32B Instruct MiniMax-H3 L0-49 Q4_K_M
Qwen · nif0
Params25.2B
Context256K
Best fitQ4_K_M 17.1 GB
Vision

Other memory sizes

Keep browsing