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
dnotitia_Smoothie Qwen3 0.6B
Qwen · Alcoft
Params596M
Context40K
Q4_K_M0.4 GB
QW
Qwen2.5 Coder 1.5B Instruct
Qwen · unsloth
Params1.54B
Context32K
Best fitF16 3.8 GB
NE
Nemotron 3.5 Bolt E4B Heretic
Nemotron · mradermacher
Params7.52B
Context64K
Q4_K_M5.3 GB
DI
DiscoveryRSI 27B
Discoveryrsi · bartowski
Params27.3B
Context256K
Q4_K_M17.4 GB
LL
OneLLM Doey V1 Llama 3.2 1B It
Llama · DoeyLLM
Params1.24B
Context128K
Best fitQ8_0 2.1 GB
GE
Gemma 3 4b It Abliterated
Gemma · mlabonne
Params3.88B
Context128K
Best fitQ3_K_M 3.7 GB
TE
TeaAI Nemo 12B
Teaai · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
QW
Qwen3 VL 2B Instruct heretic
Qwen · saidutta69
Params1.72B
Context256K
Best fitQ8_0 3.3 GB
QW
Qwen3.8 Flash Next
Qwen · vcruz305
Params51.2B
Context256K
Q4_K_M2.8 GB
SI
SIRI 7B High
Siri · mradermacher
Params7.62B
Context128K
Best fitQ2_K 4.0 GB
QW
Qwen3 0.9B A0.6B
Qwen · mradermacher
Params860M
Context40K
Best fitF16 3.2 GB
SM
SmolLM 360M
SmolLM · Felladrin
Params362M
Context2K
Smallest0.2 GB
LL
Llama 3.1 Minitron 4B Width Base
Llama · bartowski
Params4.51B
Context128K
Best fitQ3_K_L 4.0 GB
RU
rudra i1
Rudra · mradermacher
Params4.33B
Context256K
Best fitQ3_K_M 3.9 GB
LL
OneLLM Doey V1 Llama 3.2 3B Q4 K M
Llama · DoeyLLM
Params3.21B
Context128K
Best fitQ4_K_M 3.5 GB
GE
Vikhr-Gemma-2B-instruct
Gemma · mradermacher
Params2.61B
Context8K
Best fitQ6_K 3.5 GB
AP
Apertus 8B Instruct 2509
Apertus · bartowski
Params8.05B
Context64K
Q4_K_M5.1 GB
LF
LFM2.5 8B A1B Hermes Agentic Coder Abliterated v2
Lfm · mradermacher
Params8.47B
Context125K
Best fitIQ1_S 3.9 GB
RP
RPBizkit v11 12B Thinking
Rpbizkit · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
AP
Apriel 1.6 15b Thinker
Apriel · bartowski
Params14.4B
Context256K
Q4_K_M8.8 GB
QW
Crow 9B Opus 4.6 Distill Heretic_Qwen3.5
Qwen · mradermacher
Params8.95B
Context256K
Best fitIQ1_S 4.0 GB
CA
MN CaptainErisNebula 12B Chimera v1.1 Heretic Uncensored Abliterated
Captainerisnebula · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
ON
OneJev1.6 4B
Onejev · mradermacher
Params4.21B
Context256K
Best fitQ3_K_L 4.0 GB
LL
OneLLM Doey ChatQA V1 Llama 3.2 1B
Llama · DoeyLLM
Params1.24B
Context128K
Best fitQ8_0 2.1 GB
GE
Gemma-4-E2B-It
Gemma · mnsims1024
Params4.65B
Context128K
Best fitQ3_K_XL 4.0 GB
QW
Qwen3.8-27B
Qwen · hammadRahman
Params27.3B
Context256K
Q4_K_M16.5 GB
QW
Qwen2.5 1.5b Uncensored
Qwen · mradermacher
Params1.54B
Context32K
Best fitQ6_K 2.0 GB
NE
Nemotron Terminal 8B
Nemotron · mradermacher
Params8.19B
Context40K
Best fitIQ1_M 4.0 GB
AP
Apodex 1.1 Mini
Apodex · bartowski
Params35.5B
Context256K
Q4_K_M21.9 GB
OP
openchat-3.5-0106
Openchat · mradermacher
Params7.24B
Context8K
Best fitIQ2_S 3.9 GB