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
dolphin 2.9.2 qwen2 7b
Qwen · QuantFactory
Params7.62B
Context128K
Best fitQ2_K 4.0 GB
QW
Qwen3 30B A3B Claude 4.5 Opus High Reasoning 2507 ABLITERATED UNCENSORED V2
Qwen · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
OL
OLMo 1B 0724 Hf
OLMo · mradermacher
Params1.28B
Context4K
Best fitQ6_K 2.6 GB
LA
Laguna XS 2.1
Laguna · mradermacher
Params33.4B
Context256K
Q4_K_M20.3 GB
ER
ERNIE 21B A3B Claude 4.5 High OPUS Thinking
Ernie · mradermacher
Params21.8B
Context128K
Q4_K_M13.2 GB
GE
anon 1b
Gemma · scratchyone
Params1B
Context32K
Best fitBF16 2.7 GB
KA
KAT Coder V2.5 Dev
Kat · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
NA
Nanbeige4.3 33B
Nanbeige · mradermacher
Params33.1B
Context512K
Q4_K_M20.1 GB
SH
OS Shepherd 9B
Shepherd · bartowski
Params8.95B
Context256K
Q4_K_M5.9 GB
QW
Qwen3.5 35B A3B Uncensored Heretic
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
PY
Pythia 1.4b
Pythia · mradermacher
Params1.41B
Context2K
Best fitQ8_0 3.6 GB
QW
Huihui Qwen3.5 9B abliterated
Qwen · nuofang
Params8.95B
Context256K
Q4_K_M5.6 GB
LF
LFM2 2.6B Transcript
Lfm · LiquidAI
Params2.57B
Context125K
Best fitQ4_0 4.0 GB
IC
IceBlendedLatteRP-7b
Iceblendedlatterp · mradermacher
Params7.24B
Context32K
Best fitIQ2_S 3.9 GB
CO
Concept 7b V1 Full
Concept · mradermacher
Params7.62B
Context128K
Best fitQ2_K 4.0 GB
SO
Sorjin1.1 7B Instruct
Sorjin · mradermacher
Params7.62B
Context32K
Best fitQ2_K 4.0 GB
QW
Qwen3.5 9B Unredacted MAX
Qwen · mradermacher
Params8.95B
Context256K
Best fitIQ1_S 4.0 GB
QW
Qwen3 30B A3B Thinking 2507 FT
Qwen · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
QW
Qwen3.5 35B A3B Base
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
FL
FLOR 1.3B Instructed
Flor · xaviviro
Params1.41B
Context4K
Best fitQ8_0 3.6 GB
HO
K2 Horizon 0.9B
Horizon · NANI-Nithin
Params1.08B
Context128K
Best fitBF16 3.1 GB
EI
Einstein-v4-7B
Einstein · mradermacher
Params7.24B
Context32K
Best fitIQ2_S 3.9 GB
CI
Cirque 12B
Cirque · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
LL
Meta-Llama-3-8B-Instruct
Llama · qwp4w3hyb
Params8B
Context8K
Best fitIQ2_XXS 4.0 GB
HE
Hemmingway 1.5 Unlocked
Hemmingway · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
LL
Lebanese Llama 3.1 8b
Llama · mradermacher
Params8B
Context128K
Best fitIQ2_XXS 4.0 GB
GA
GameScaling 2B S3
Gamescaling · mradermacher
Params2.39B
Context256K
Best fitQ8_0 3.5 GB
NE
NeonLLM-Base
Neonllm · mradermacher
Params7.24B
Context8K
Best fitIQ2_S 3.9 GB
OR
Ornith 1.5 35B A3B BigBang MTP
Ornith · EryriLabs
Params1.86B
Context256K
Best fitQ8_0 3.2 GB
NA
Nano.Imp Creative.Writing Heretic 3.2 1B
Nano · mradermacher
Params1.5B
Context128K
Best fitQ6_K 2.0 GB