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
Qwen3.5 9B DFlash
Qwen · magnitudedev
Params1.29B
Context40K
Best fitQ8_0 2.1 GB
MA
Magidonia 24B v4.2.0
Magidonia · bartowski
Params23.6B
Context128K
Q4_K_M14.3 GB
MI
Voxtral-Mini-4B-Realtime-2602
Mistral · ggml-org
Params3.43B
Context128K
Best fitQ4_K_M 3.9 GB
NO
Novel Humanize 4b
Novel · mradermacher
Params4.02B
Context40K
Best fitIQ4_XS 4.0 GB
TO
ToolSpace 8B
Toolspace · mradermacher
Params8.19B
Context64K
Best fitIQ1_M 4.0 GB
TI
TinyLlama-1.1B-DavidAttenborough
Tinyllama · mradermacher
Params1.1B
Context4K
Best fitQ6_K 1.6 GB
SE
Securecoder 30b Pro v3 Merged
Securecoder · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
GP
DMind-3
gpt-oss · Mungert
Params20.9B
Context128K
Q4_K_M16.0 GB
FR
Frontis MA1 35B
Frontis · bartowski
Params35.5B
Context256K
Q4_K_M21.9 GB
QW
Qwen3.6 35B A3B Brainwaves Nex Uncensored
Qwen · mradermacher
Params35.5B
Context256K
Q4_K_M21.7 GB
QW
BigBubba Qwen3.6 27B
Qwen · bartowski
Params27.3B
Context256K
Q4_K_M17.8 GB
MI
Huihui MiniCPM V 4.6 Thinking Abliterated
MiniCPM · mradermacher
Params752M
Context256K
Best fitQ5_K_S 1.5 GB
QW
SignOfFour
Qwen · mradermacher
Params34.7B
Context32K
Q4_K_M21.2 GB
VU
VulnLLM R 7B
Vulnllm · mradermacher
Params7.62B
Context32K
Best fitQ2_K 4.0 GB
QW
Qwen2 VL 2B Instruct
Qwen · second-state
Params1.54B
Context32K
Best fitF16 3.8 GB
QW
Qwen3.5 9B OmniCoder Claude Polaris
Qwen · mradermacher
Params8.95B
Context256K
Best fitIQ1_S 4.0 GB
JA
Jan-Nano
Jan · unsloth
Params4B
Context40K
Best fitIQ4_XS 4.0 GB
GP
GPT OSS Cybersecurity 20B Merged
gpt-oss · mradermacher
Params20.9B
Context128K
Q4_K_M15.8 GB
AN
Anime Girl 1.5B
Anime · mradermacher
Params1.54B
Context32K
Best fitQ6_K 2.0 GB
GE
gemma 4 E2B it qat q4 0 heretic
Gemma · FadedRedStar
Params4.63B
Context128K
Best fitQ4_0 3.2 GB
GE
Gemma 4 E2B It Uncensored MAX
Gemma · mradermacher
Params4.65B
Context128K
Q4_K_M3.4 GB
FA
Falcon-H1-0.5B-Instruct
Falcon · unsloth
Params521M
Context16K
Best fitBF16 1.7 GB
QW
Qwen3 VL 32B Thinking
Qwen · bartowski
Params32.8B
Context256K
Q4_K_M19.8 GB
SM
SmolVLM2 2.2B Instruct Agentic GUI
Smolvlm · bartowski
Params1.81B
Context8K
Best fitQ8_0 4.0 GB
MA
Marco Mini Instruct
Marco · mradermacher
Params17.3B
Context32K
Q4_K_M10.5 GB
LL
Llama 3.1 8B Lexi Uncensored V2
Llama · mradermacher
Params8B
Context128K
Best fitIQ2_XXS 4.0 GB
GR
granite embedding 125m english
Granite · bartowski
Params124M
Context512
Best fitF16 1.1 GB
CA
CaptainErisNebula 12B Chimera v1.1
Captainerisnebula · Lewdiculous
Params12.2B
Context1000K
Q4_K_M7.5 GB
QW
Qwen3.8 Flash Next
Qwen · kingjones777
Params3.88B
Context256K
Best fitQ4_0 3.6 GB
CY
Blackfrost-AI/CYBER-FROST-3.8-BF16
Cyber · 0xSojalSec
Params177B
Context256K
Best fitQ4_K_M 4.0 GB