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.
QW
Models Qwen Qwen3 4B
Qwen · MaziyarPanahi
Params4B
Context40K
Best fitQ3_K_L 3.9 GB
SM
SmolLM2 135M Instruct
SmolLM · unsloth
Params135M
Context8K
Best fitF16 1.0 GB
GE
gemma 4 E2B it qat
Gemma · unsloth
Params4.63B
Context128K
Best fitQ4_K_XL 3.2 GB
QW
Huihui Qwen3.5 4B Abliterated
Qwen · mradermacher
Params4.21B
Context256K
Best fitIQ4_XS 4.0 GB
QW
Models Qwen Qwen3 1.7B
Qwen · MaziyarPanahi
Params2.03B
Context40K
Best fitQ6_K 3.1 GB
GE
gemma 4 E4B it qat mobile
Gemma · unsloth
Params7.46B
Context128K
Best fitQ2_K_XL 3.9 GB
SE
SeaLLMs SeaLLMs v3 7B Chat
Seallms · RichardErkhov
Params7.62B
Context—
Best fitQ2_K 3.0 GB
QW
Ternary-Bonsai-2-4B
Qwen · prism-ml
Params782M
Context256K
Best fitBF16 3.1 GB
QW
Qwen2.5 Coder 7B Instruct
Qwen · bartowski
Params7.62B
Context32K
Best fitQ2_K 4.0 GB
TR
Translategemma 4b It
Translategemma · bullerwins
Params3.88B
Context128K
Best fitQ4_K_S 4.0 GB
KI
kitten tts 2
Kitten · KittenML
Params1.73B
Context40K
Smallest1.0 GB
BG
bge m3
BGE · gpustack
Params567M
Context8K
Q4_K_M0.4 GB
QW
Qwen3.8-Flash-Next
Qwen · ggml-org
Params177B
Context256K
Best fitQ4_0 2.9 GB
LL
Meta Llama 3 8B Instruct
Llama · MaziyarPanahi
Params8B
Context8K
Best fitIQ1_M 3.7 GB
GE
Gemma 3 4b It
Gemma · lmstudio-community
Params3.88B
Context128K
Best fitQ3_K_L 3.9 GB
ST
stories15M MOE
Stories · ggml-org
Params8M
Context256
Smallest0.0 GB
NE
NVIDIA Nemotron 3.5 Bolt 74B A9B
Nemotron · unsloth
Params74B
Context256K
Smallest1.0 GB
FA
Jiqing tiny random falcon
Falcon · RichardErkhov
Params—
Context—
Best fitIQ3_M 0.5 GB
QW
Qwen3.5 0.8B
Qwen · ggml-org
Params773M
Context256K
Best fitBF16 2.5 GB
HU
Cyber Tiel Coder 35B A3B
Huihui · peculiar-ragdoll
Params34.7B
Context256K
Q4_K_M22.1 GB
FR
FrontTerrain-HARP-1B
Frontterrain · frontterrain
Params123M
Context512
Best fitF16 0.8 GB
GE
Winnow 12B
Gemma · EldanRing
Params423M
Context256K
Best fitBF16 2.4 GB
SM
SmolLM2 135M Instruct
SmolLM · bartowski
Params135M
Context8K
Best fitF16 1.0 GB
GE
Gemma-3N-E2B-It
Gemma · unsloth
Params4.46B
Context32K
Best fitQ4_0 4.0 GB
QW
Qwen3.8 27B pi
Qwen · bytkim
Params27B
Context256K
Best fitQ8_0 3.8 GB
GE
Gemma 2 2b It
Gemma · bartowski
Params2.61B
Context8K
Best fitQ6_K_L 3.7 GB
GR
ibm granite granite 20b code instruct
Granite · RichardErkhov
Params1.9B
Context—
Best fitIQ3_S 1.5 GB
LL
Llama 3.2 3B Instruct
Llama · lmstudio-community
Params3.21B
Context128K
Best fitQ4_K_M 3.5 GB
LL
Llama3.3 8B Instruct Thinking Heretic Uncensored Claude 4.5 Opus High Reasoning
Llama · mradermacher
Params8B
Context128K
Best fitIQ2_XXS 4.0 GB
QW
Qwen3.5-2B-Uncensored-HauhauCS-Aggressive
Qwen · HauhauCS
Params1.88B
Context256K
Best fitQ8_0 2.9 GB