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.
FL
flux2 klein 4b uncensored text encoder
Flux · ponpoke
Params4B
Context—
Best fitQ4_K_M 3.3 GB
LY
Lythri 7B A4B
Lythri · mradermacher
Params7.46B
Context128K
Q4_K_M5.3 GB
QW
Qwen2.5 3B
Qwen · bartowski
Params3.09B
Context32K
Best fitQ6_K_L 3.4 GB
TE
Tess 4.5 27B
Tess · bartowski
Params27.3B
Context256K
Q4_K_M17.4 GB
SM
SmolLM2 1.7B Instruct
SmolLM · HuggingFaceTB
Params1.71B
Context8K
Best fitQ4_K_M 3.2 GB
SP
Raptor 0.6 4B
Spark · OsaurusAI
Params4.1B
Context1024K
Q4_K_M2.6 GB
ME
MedGo i1
Medgo · mradermacher
Params32.8B
Context40K
Q4_K_M19.8 GB
OM
D1 Omni 2B
Omni · LiquidAI
Params1.73B
Context125K
Best fitQ8_0 4.0 GB
LL
Llama Joycaption Beta One Hf Llava
Llama · mradermacher
Params8B
Context128K
Best fitIQ2_XXS 4.0 GB
QW
Qwen3.6-35B-A3B
Qwen · TokenTinkerer
Params34.7B
Context256K
Best fitQ4_K_M 1.7 GB
QW
Dolphin3.0 Qwen2.5 3B
Qwen · bartowski
Params3.09B
Context32K
Best fitQ6_K_L 3.4 GB
NE
NVIDIA Nemotron 3.5 Bolt Turbo Brilliance 50x 74B A9B 24GB
Nemotron · DavidAU
Params74B
Context256K
Smallest1.0 GB
QW
Huihui Qwen3.5 2B Abliterated
Qwen · mradermacher
Params1.88B
Context256K
Best fitQ8_0 2.9 GB
MI
Mistral Small 4 119B 2603 Heretic
Mistral · Rioky
Params119B
Context1024K
Q4_K_M72.2 GB
LF
LFM2 1.2B
Lfm · LiquidAI
Params1.17B
Context125K
Best fitF16 3.9 GB
HO
K2-Horizon-MoVA-36B-A4B
Horizon · bartowski
Params37.4B
Context512K
Q4_K_M22.7 GB
QW
Qwen3 VL 4B Instruct
Qwen · bartowski
Params4B
Context256K
Best fitIQ4_XS 4.0 GB
JU
Julia-1
Julia · ggml-org
Params144M
Context8K
Best fitBF16 1.1 GB
AV
ava lfm25 toolcall
Ava · vitorcalvi
Params1.17B
Context125K
Best fitQ4_0 2.3 GB
GL
GLM 5.3 Flash abliterated Maya M
GLM · alesha-pro
Params370B
Context64K
Smallest0.0 GB
QW
Qwen3 4B Abliterated
Qwen · bartowski
Params4B
Context40K
Best fitIQ4_XS 4.0 GB
SK
Skyfall 31B v4.2
Skyfall · bartowski
Params31.4B
Context128K
Q4_K_M19.3 GB
NS
NSFW flash
Nsfw · UnfilteredAI
Params2.24B
Context4K
Best fitQ4_K_M 4.0 GB
QW
Qwen3.8 35B A3B Distill
Qwen · IsValorum
Params34.7B
Context256K
Best fitQ8_0 3.2 GB
MI
MiniCPM5 2B heretic abliterated
MiniCPM · Abiray
Params2.52B
Context128K
Best fitQ8_0 3.5 GB
EM
Embeddinggemma 300m Qat Q4_0 Unquantized
Embeddinggemma · unsloth
Params303M
Context2K
Best fitF32 1.9 GB
QW
Qwen2.5 3B Instruct Uncensored
Qwen · mradermacher
Params3.09B
Context32K
Best fitQ6_K 3.3 GB
MI
Ministral-3-3B-Reasoning-2512
Mistral · unsloth
Params3.43B
Context256K
Best fitQ5_K_XL 3.9 GB
NU
NuExtract3
Nuextract · numind
Params4.33B
Context256K
Best fitQ3_K_M 3.9 GB
PA
PaddleOCR VL 1.6
Paddleocr · LunarOilRig
Params467M
Context128K
Best fitQ4_K_M 1.0 GB