GGUF models that fit in 4 GB

79024 GGUF language models have at least one quant whose estimated memory use is 4 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 1280000K tokens.

Most downloadedNewestLargestLongest contextSmallest
LL
Impish_LLAMA_4B_V2
Llama · SicariusSicariiStuff
Params4.5B
Context128K
Best fitQ3_K_L 4.0 GB
GGUF
QW
Models Qwen Qwen3 4B Thinking 2507
Qwen · MaziyarPanahi
Params4B
Context256K
Best fitQ3_K_L 3.9 GB
Reasoning
NE
NeoHorse-1-4B
Neohorse · ngquocvinh
Params4.21B
Context256K
Best fitQ3_K_L 4.0 GB
ReasoningTool use
TI
Tinylaya For Testing
Tinylaya · ggml-org
Params90M
Context8K
Best fitQ8_0 0.7 GB
GGUF
QW
Qwen3.8 27B Pi
Qwen · bartowski
Params27.3B
Context256K
Q4_K_M17.4 GB
CodingReasoningTool use
SM
SmolVLM2 500M Video Instruct
Smolvlm · ggml-org
Params409M
Context8K
Best fitF16 1.7 GB
Vision
SM
SmolVLM 256M Instruct
Smolvlm · ggml-org
Params163M
Context8K
Best fitF16 1.0 GB
Vision
LF
Lfm2.5-Vl-3B
Lfm · unsloth
Params2.7B
Context125K
Best fitIQ4_XS 4.0 GB
Vision
OR
Ornith 1.5 122B UNCENSORED
Ornith · dealignai
Params125B
Context256K
Best fitQ8_0 2.3 GB
Vision
QW
Qwen2.5 Math 7B Instruct
Qwen · bartowski
Params7.62B
Context4K
Best fitQ2_K 4.0 GB
GGUF
MI
Ministral 3 3B Instruct 2512
Mistral · bartowski
Params3.43B
Context256K
Best fitQ5_K_L 3.9 GB
Vision
QW
Qwen3.5 122B A10B
Qwen · bartowski
Params125B
Context256K
Q4_K_M77.6 GB
Vision
LL
dolphin 2.9 llama3 8b
Llama · bartowski
Params8B
Context8K
Best fitIQ2_XXS 4.0 GB
CodingTool use
QW
Qwen3 0.6B Abliterated
Qwen · mradermacher
Params596M
Context40K
Best fitF16 2.6 GB
GGUF
QW
Qwen3 0.6B Heretic Abliterated Uncensored
Qwen · mradermacher
Params596M
Context40K
Best fitQ5_K_S 1.9 GB
GGUF
MI
Ministral-3-8B-Instruct-2512
Mistral · unsloth
Params8.49B
Context256K
Best fitIQ1_S 3.9 GB
Vision
QW
Qwen3 0.6B Heretic
Qwen · mradermacher
Params596M
Context40K
Best fitF16 2.6 GB
ReasoningTool use
VI
VieNeu TTS v2
Vieneu · pnnbao-ump
Params294M
Context4K
Smallest0.2 GB
Coding
SM
SmolLM2 360M Instruct
SmolLM · HuggingFaceTB
Params362M
Context8K
Best fitQ8_0 1.2 GB
GGUF
LL
Hermes 3 Llama 3.2 3b Base Fft Chatml Rerun 8xh100 E4 2024 11 24 4k Steps
Llama · bartowski
Params3.21B
Context128K
Best fitQ5_K_L 3.9 GB
RoleplayTool use
QW
Qwen3 Next 80B A3B Instruct
Qwen · bartowski
Params80B
Context256K
Q4_K_M48.7 GB
GGUF
QW
Qwen3.5-2B
Qwen · unsloth
Params1.94B
Context256K
Best fitQ8_K_XL 3.8 GB
Vision
QW
Qwen_Qwen3.5 0.8B
Qwen · lmstudio-community
Params752M
Context256K
Best fitQ8_0 1.7 GB
Vision
QW
Z Image Qwen 3 4b text encoder
Qwen · worstplayer
Params4B
Context40K
Best fitIQ4_XS 4.0 GB
Coding
QW
Qwen2.5 VL 3B Instruct
Qwen · lmstudio-community
Params3.09B
Context125K
Best fitQ6_K 3.3 GB
Vision
LL
testmod koen llama2 13b dpotrain testver
Llama · RichardErkhov
Params13B
Context—
Best fitQ3_K_M 2.9 GB
GGUF
OR
Ornith 1.5 9B
Ornith · bartowski
Params8.95B
Context256K
Q4_K_M5.9 GB
Vision
QW
Qwen2.5 Coder 32b Instruct Heretic Sft
Qwen · mradermacher
Params32.8B
Context32K
Q4_K_M19.9 GB
Coding
QW
Huihui Qwen3 4B Instruct 2507 Abliterated
Qwen · mradermacher
Params4B
Context256K
Best fitIQ4_XS 4.0 GB
GGUF
GE
Huihui gemma 4 E4B it qat q4 0 unquantized abliterated
Gemma · huihui-ai
Params7.46B
Context128K
Best fitBF16 0.8 GB
Vision

Other memory sizes

Keep browsing