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.
FE
Feyospace S1 OBLITERATED
Feyospace · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
QW
Qwen3.8 9B
Qwen · hakergeniusz
Params9.2B
Context256K
Q4_K_M5.8 GB
BT
badtheorylabs BTL 4
Btl · bartowski
Params34.7B
Context256K
Q4_K_M21.4 GB
QW
Qwen3.8-27B
Qwen · Fix-AI
Params27.3B
Context256K
Q4_K_M16.5 GB
QW
Qwen2.5 1.5B Instruct
Qwen · mradermacher
Params1.54B
Context32K
Q4_K_M1.0 GB
CO
CorX3.8 27B
Corx · mradermacher
Params26.9B
Context256K
Q4_K_M16.5 GB
LL
Hermes-2-Theta-Llama-3-8B-32k
Llama · mradermacher
Params8B
Context32K
Best fitIQ2_XXS 4.0 GB
FA
FableForge
Fableforge · fableforge-ai
Params1.54B
Context32K
Best fitF16 3.8 GB
TR
TripleTrouble
Tripletrouble · mradermacher
Params34.7B
Context32K
Q4_K_M21.2 GB
QW
Qwen3.5 9B The Bradbury F451 Pro Writer Uncensored Heretic
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
LL
Llama-3.3-8B-Instruct
Llama · Mungert
Params8B
Context8K
Q4_K_M5.3 GB
QW
Qwen3 VL 32B Instruct Abliterated v1
Qwen · mradermacher
Params32.8B
Context256K
Q4_K_M19.8 GB
NE
nexus security
Nexus · King3Djbl
Params1.54B
Context32K
Best fitF16 3.8 GB
QW
Qwen_Qwen3 1.7B
Qwen · Alcoft
Params2.03B
Context40K
Best fitQ6_K_XL 3.8 GB
GL
Gliese OCR 7B Post2.0 Final
Gliese · prithivMLmods
Params7.62B
Context125K
Best fitQ2_K 4.0 GB
GE
Gemma 4 31B It Assistant
Gemma · AtomicChat
Params470M
Context256K
Best fitF16 3.6 GB
DI
Sf Diogenes v0.1
Diogenes · mradermacher
Params79.7B
Context256K
Q4_K_M48.4 GB
QW
Qwen3 TTS 12Hz 0.6B
Qwen · BricksDisplay
Params661M
Context32K
Best fitF32 3.8 GB
MA
MAmmoTH2-8B-Plus
Mammoth · mradermacher
Params8B
Context8K
Best fitIQ2_XXS 4.0 GB
QW
Qwen2.5 0.5B
Qwen · bartowski
Params494M
Context32K
Best fitF32 2.6 GB
GA
GaMS3 12B Multimodal
Gams · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
RI
Riva Translate 4B Instruct v1.1
Riva · mradermacher
Params4.18B
Context8K
Best fitQ3_K_L 4.0 GB
QW
Qwen3.5 27B Claude 4.6 OS Auto Variable Heretic Uncensored Thinking
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
QW
Qwen3 VL 4B Instruct Heretic
Qwen · mradermacher
Params4B
Context256K
Best fitIQ4_XS 4.0 GB
MI
Ministral 3 8B Reasoning 2512 It
Mistral · mradermacher
Params8.49B
Context256K
Best fitIQ1_M 3.9 GB
ER
ERNIE 4.5 0.3B PT
Ernie · bartowski
Params361M
Context128K
Best fitBF16 1.4 GB
LF
LFM3 1.7B
Lfm · ngquocvinh
Params1.73B
Context256K
Best fitQ8_0 4.0 GB
VI
Vistral 7B ties
Vistral · mradermacher
Params5.5B
Context32K
Best fitIQ3_M 4.0 GB
GP
Gpt2 Xl
Gpt · mradermacher
Params1.64B
Context1K
Best fitIQ4_XS 4.0 GB
QW
Qwen3 Coder 42B A3B Instruct TOTAL RECALL MASTER CODER M 768k Ctx
Qwen · mradermacher
Params42.4B
Context768K
Q4_K_M25.7 GB