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.
MA
MAI Gym 9B
Mai · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
GR
Groot 19B A3B 261023
Groot · mradermacher
Params19B
Context256K
Q4_K_M11.7 GB
QW
Ostrich 27B 261008 Qwen3.8 Abliterated
Qwen · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
CA
CalibForge 35B A3B
Calibforge · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
QW
ThinCtx Qwen3.5 2B
Qwen · mradermacher
Params1.88B
Context256K
Best fitQ6_K 2.5 GB
AC
ActIO-UI-7B-RLVR
Actio · mradermacher
Params7.62B
Context125K
Best fitQ2_K 4.0 GB
LB
LBS 27B
Lbs · bartowski
Params26.9B
Context256K
Q4_K_M17.2 GB
LL
chargoddard llama 2 26b trenchcoat stack
Llama · RichardErkhov
Params25.7B
Context—
Best fitIQ4_XS 3.4 GB
HO
K2 Horizon 7B UnrealEngine
Horizon · mradermacher
Params9B
Context512K
Q4_K_M5.6 GB
QW
Qwen3.6 35B A3B Claude 4.7 Opus Reasoning Distilled
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
PR
Bu 30b A3B Preview
Preview · bartowski
Params30.5B
Context256K
Q4_K_M18.6 GB
ME
Meltemi 7B Instruct v1.5
Meltemi · mradermacher
Params7.48B
Context32K
Best fitIQ2_S 4.0 GB
GR
Granite 8b Code Instruct
Granite · duyntnet
Params8.05B
Context4K
Best fitIQ2_XXS 3.9 GB
LF
Lfm2.5-230M
Lfm · unsloth
Params230M
Context125K
Best fitBF16 1.4 GB
VA
VanMach 7B
Vanmach · mradermacher
Params7.71B
Context128K
Best fitQ2_K 4.0 GB
QW
Qwen3.6 21B IQ Ultra Heretic Uncensored Thinking
Qwen · mradermacher
Params20.8B
Context256K
Q4_K_M12.9 GB
SP
Spark X2.6 4B
Spark · mradermacher
Params4.11B
Context1024K
Best fitQ3_K_M 3.9 GB
QW
Qwen2.5 VL 3B Instruct Abliterated
Qwen · mradermacher
Params3.09B
Context125K
Best fitQ6_K 3.3 GB
QW
Qwen2-7B
Qwen · legraphista
Params7.62B
Context128K
Best fitQ2_K 4.0 GB
MI
MiniCPM5 1B Agentic Tooluse v3
MiniCPM · ewin-reg
Params1.08B
Context128K
Best fitF16 2.9 GB
LL
Llama 3.3 8B Thinking Gemini Flash 11000x 128k
Llama · mradermacher
Params8B
Context128K
Best fitIQ2_XXS 4.0 GB
CO
Command A Plus 05 2026
Command · bartowski
Params218B
Context195K
Q4_K_M135.1 GB
QW
Qwen3 14B GPT 5.2 High Reasoning Distill
Qwen · TeichAI
Params14.8B
Context40K
Best fitIQ2_M 1.8 GB
QW
Qwen2.5 1.5B Instruct Abliterated
Qwen · mradermacher
Params1.54B
Context32K
Best fitF16 3.8 GB
KA
Kataguru Industry MVP 27B v1.1
Kataguru · kataguru
Params26.9B
Context256K
Q4_K_M2.0 GB
GR
Granite 4.2 30b
Granite · bartowski
Params29.3B
Context128K
Q4_K_M18.0 GB
EX
EXAONE 3.5 2.4B Instruct 2
Exaone · ThomasBaruzier
Params2.67B
Context32K
Best fitQ8_0 4.0 GB
JA
JapanRailwayLLM
Japanrailwayllm · mradermacher
Params9.2B
Context8K
Q4_K_M5.8 GB
LF
LFM2 350M Extract
Lfm · LiquidAI
Params354M
Context125K
Best fitF16 1.7 GB
GE
Gemma 4 E4B IT ABLITERATED UNCENSORED PHILADELPHIA CLASS
Gemma · mradermacher
Params7.46B
Context128K
Q4_K_M5.3 GB