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
Qwen2.5 Coder 14B Instruct 3MPER0RR Abliterated
Qwen · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
BO
Boptruth Agatha 7B i1
Boptruth · mradermacher
Params7.24B
Context128K
Best fitIQ2_S 3.9 GB
EM
Emotion Companion 7b
Emotion · mradermacher
Params7.62B
Context32K
Best fitQ2_K 4.0 GB
SM
SmolLM2 135M Instruct
SmolLM · QuantFactory
Params135M
Context8K
Best fitQ2_K 0.8 GB
LL
Fireball Meta Llama 3.2 8B Instruct agent 003 128k code DPO i1
Llama · mradermacher
Params8B
Context128K
Best fitIQ2_XXS 4.0 GB
LI
LightOnOCR 3 4B
Lightonocr · mradermacher
Params4.21B
Context256K
Best fitQ3_K_L 4.0 GB
QW
Qwen2.5 7B Instruct Heretic
Qwen · mradermacher
Params7.62B
Context32K
Best fitQ2_K 4.0 GB
QW
Qwen3.6 35B A3B Abliterated
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
QW
Qwen3.5 4B RpRMax v1
Qwen · mradermacher
Params4.21B
Context256K
Best fitQ3_K_L 4.0 GB
GE
Gemma 3 4b It Abliterated v2
Gemma · mlabonne
Params3.88B
Context128K
Best fitQ3_K_M 3.7 GB
QW
Qwen2.5 Coder 1.5B Instruct
Qwen · alphaduriendur
Params1.54B
Context32K
Best fitQ4_K_M 1.7 GB
CH
ChatGPT 5 Q8 0
Chatgpt · Hack337
Params494M
Context32K
Best fitQ8_0 1.1 GB
IC
IceEspressoRPv6 i1
Iceespressorpv · mradermacher
Params7.24B
Context32K
Best fitIQ2_S 3.9 GB
GP
gpt2 i1
Gpt · mradermacher
Params163M
Context1K
Best fitIQ1_S 0.9 GB
NO
NousCoder 14B
Nouscoder · bartowski
Params14.8B
Context80K
Q4_K_M9.0 GB
LL
Llama 3.1 8B
Llama · mradermacher
Params8B
Context128K
Best fitIQ2_XXS 4.0 GB
LL
Llama-3-Instruct-8B-SPPO-Iter3
Llama · legraphista
Params8B
Context8K
Best fitIQ2_XXS 4.0 GB
EX
EXAONE 3.5 2.4B Instruct
Exaone · lmstudio-community
Params2.67B
Context32K
Best fitQ8_0 4.0 GB
GL
GLM 4.7 Flash Name NSFW
GLM · mradermacher
Params30B
Context198K
Q4_K_M18.1 GB
AS
astrollama 3 8b chat aic i1
Astrollama · mradermacher
Params8B
Context8K
Best fitIQ2_XXS 4.0 GB
IQ
IQuest Coder V1 40B Instruct
Iquest · mradermacher
Params39.8B
Context128K
Q4_K_M24.0 GB
SK
Skywork OR1 Math 7B
Skywork · bartowski
Params7.62B
Context128K
Best fitQ2_K 4.0 GB
IN
Internlm2 Math Base 7b
InternLM · mradermacher
Params7.74B
Context8K
Best fitIQ2_XS 4.0 GB
PR
PreciseCoder 4B
Precisecoder · mradermacher
Params4.21B
Context256K
Best fitQ3_K_L 4.0 GB
QW
Qwen2 Math 1.5B Instruct
Qwen · legraphista
Params1.54B
Context4K
Best fitBF16 3.8 GB
PY
Pythia 160m
Pythia · mradermacher
Params162M
Context2K
Best fitIQ1_S 0.9 GB
IN
Index Nailong 2B
Index · mradermacher
Params1.88B
Context256K
Best fitQ6_K 2.5 GB
GP
Gpt Oss Sanguine 20b v1
gpt-oss · mradermacher
Params20.9B
Context128K
Q4_K_M15.8 GB
QW
Qwen3 Reranker 0.6B
Qwen · mradermacher
Params596M
Context40K
Best fitF16 2.6 GB
QW
Qwen3 Esper3 Reasoning CODER Instruct 6B Brainstorm20x
Qwen · mradermacher
Params5.94B
Context40K
Best fitIQ1_M 3.9 GB