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.
OM
d1-omni-600M
Omni · LiquidAI
Params381M
Context125K
Best fitBF16 1.9 GB
GL
GLM 4.6V Flash
GLM · bartowski
Params9.4B
Context128K
Q4_K_M6.2 GB
QW
Qwen2.5 VL 32B Instruct Unredacted MAX
Qwen · mradermacher
Params32.8B
Context125K
Q4_K_M19.9 GB
MI
MiniCPM V 2 6
MiniCPM · openbmb
Params7.61B
Context32K
Best fitQ2_K 4.0 GB
QW
Qwen3.8 27B Uncensored Heretic Abliterated
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
OR
Huihui Ornith 1.0 9B abliterated MTP
Ornith · huihui-ai
Params2.28B
Context256K
Best fitQ8_0 4.0 GB
LL
Dolphin 3.0 Llama 3.2 3B
Llama · bartowski
Params3.21B
Context128K
Best fitQ5_K_L 3.9 GB
LF
LFM2 700M
Lfm · LiquidAI
Params742M
Context125K
Best fitF16 2.8 GB
DE
DeepSeek Coder V2 Lite Instruct Abliterated
DeepSeek · mradermacher
Params15.7B
Context160K
Q4_K_M10.4 GB
LY
Lythri 4B A2B
Lythri · mradermacher
Params4.63B
Context128K
Best fitQ2_K_S 4.0 GB
TA
UI TARS 1.5 7B
Tars · mradermacher
Params7.62B
Context125K
Best fitQ2_K 4.0 GB
XI
Xiaomi OCR 0
Xiaomi · prithivMLmods
Params752M
Context256K
Best fitBF16 2.4 GB
GE
Gemma 3 4B VL It Gemini Pro Heretic Uncensored Thinking
Gemma · Andycurrent
Params3.88B
Context128K
Best fitQ3_K_M 3.7 GB
QW
qwen2-0_5b-instruct
Qwen · Qwen
Params494M
Context32K
Q4_K_M0.4 GB
QW
Qwen2.5 Coder 3B Instruct Abliterated
Qwen · bartowski
Params3.09B
Context32K
Best fitQ6_K_L 3.4 GB
GP
OpenAI Gpt Oss 20B Claude 4.5 Opus Heretic Uncensored
gpt-oss · mradermacher
Params20.9B
Context128K
Q4_K_M15.8 GB
QW
Qwen2.5 Coder 7B Instruct Uncensored
Qwen · BlossomsAI
Params7.62B
Context32K
Best fitQ2_K 4.0 GB
LF
LFM2.5-1.2B-Thinking
Lfm · LiquidAI
Params1.17B
Context125K
Best fitBF16 3.9 GB
MU
Music Flamingo Hf
Music · mradermacher
Params7.61B
Context32K
Best fitQ2_K 4.0 GB
MI
MiniCPM V 4.7 35B A3B
MiniCPM · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
QW
Qwen2.5 0.5B Instruct
Qwen · lmstudio-community
Params494M
Context32K
Best fitQ6_K 1.1 GB
QW
Qwen3.5-0.8B
Qwen · unsloth
Params773M
Context256K
Best fitBF16 2.5 GB
QW
Qwen3.8-27B
Qwen · 6block
Params27B
Context256K
Q4_K_M17.7 GB
LL
Nidum Llama 3.2 3B Uncensored
Llama · lemuralabs
Params3.21B
Context128K
Best fitQ5_K_M 3.8 GB
QW
Qwen3.6 35B A3B Anko
Qwen · bartowski
Params34.7B
Context256K
Q4_K_M21.4 GB
NA
Nanonets-Ocr-S
Nanonets · unsloth
Params3.1B
Context125K
Best fitQ6_K_XL 3.6 GB
QW
Qwen3.8 Flash Next Uncensored ik llama
Qwen · ji-farthing
Params177B
Context—
Smallest2.2 GB
VE
UI Venus 2 9B
Venus · bartowski
Params8.95B
Context256K
Q4_K_M5.9 GB
MU
Murasaki 4B v0.3
Murasaki · mradermacher
Params4.41B
Context32K
Best fitQ3_K_M 4.0 GB
QW
Qwopus3.8 27B Flash V2 Abliterated
Qwopus · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB