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.

Most downloadedNewestLargestLongest contextSmallest
GE
gemma 4 E2B it qat MTP
Gemma · magnitudedev
Params77M
Context128K
Best fitQ4_0 0.6 GB
GGUF
BU
Buddy E4B v2
Buddy · mradermacher
Params7.5B
Context128K
Q4_K_M5.3 GB
GGUF
OE
Oellm 9b 128k Theta32M
Oellm · mradermacher
Params9.1B
Context128K
Q4_K_M5.7 GB
GGUF
GP
Gpt2 Large
Gpt · mradermacher
Params838M
Context1K
Best fitQ6_K 2.7 GB
GGUF
IR
Irbis-7b-v0.1
Irbis · mradermacher
Params7.47B
Context32K
Best fitIQ2_S 4.0 GB
GGUF
GE
Gemma 4 E4B It Ultra Uncensored Heretic
Gemma · mradermacher
Params7.5B
Context128K
Q4_K_M5.3 GB
GGUF
GE
Gemma 4 E4B It The DECKARD Expresso Universe HERETIC UNCENSORED Thinking
Gemma · mradermacher
Params7.5B
Context128K
Q4_K_M5.3 GB
CodingReasoningRoleplay
QW
Qwen2.5 0.5B Instruct
Qwen · legraphista
Params494M
Context32K
Best fitBF16 1.6 GB
GGUF
QW
Gliese Qwen3.5 9B Abliterated Caption
Qwen · mradermacher
Params8.95B
Context256K
Best fitIQ1_S 4.0 GB
Reasoning
JE
Jebadiah 9b v2 1
Jebadiah · bartowski
Params9.2B
Context256K
Q4_K_M6.0 GB
Vision
QW
qwen rp 0.5b
Qwen · andybanana
Params494M
Context32K
Best fitQ4_K_M 1.0 GB
Roleplay
ST
Stellar Witch 12B Heretic
Stellar · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
GGUF
GE
Gemma-4-E4B-It
Gemma · Hlebek
Params7.52B
Context128K
Best fitBF16 2.1 GB
ReasoningTool useVision
CA
Carbon X
Carbon · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
ReasoningTool use
TI
TinyLlama 1.1B Chat v1.0
Tinyllama · second-state
Params1.1B
Context2K
Best fitQ8_0 1.9 GB
GGUF
GE
Gemini Nano Gemmafied
Gemma · mradermacher
Params3.24B
Context8K
Best fitQ6_K 3.4 GB
GGUF
CO
Q2.5 ColdBrew R1 ForgeWide SAFE
Coldbrew · mradermacher
Params9.5B
Context128K
Best fitIQ2_XXS 3.9 GB
Reasoning
TR
Translategemma 4b It
Translategemma · mradermacher
Params3.88B
Context128K
Best fitIQ4_NL 4.0 GB
GGUF
CO
ContextPilot 14B
Contextpilot · bartowski
Params14.8B
Context40K
Q4_K_M9.3 GB
Tool use
QW
Qwen3.5 27B Writer V2 Uncensored Heretic
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
GGUF
LL
Llama 3.2 3B Instruct Abliterated
Llama · Hasaranga85
Params3.61B
Context128K
Best fitQ4_K_M 3.7 GB
GGUF
GE
Locus Gemma 4 E2B
Gemma · mradermacher
Params7.46B
Context128K
Q4_K_M5.3 GB
GGUF
QW
Prettybird_Bce_Basic_Coder_8B
Qwen · mradermacher
Params7.6B
Context63K
Best fitQ2_K 4.0 GB
Coding
CY
Cydonia 24B v4.1
Cydonia · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
SM
SmolLM2-135M
SmolLM · ggml-org
Params135M
Context8K
Best fitBF16 1.0 GB
GGUF
QW
Qwen3.5 2B
Qwen · gguf
Params1.94B
Context256K
Best fitQ8_0 3.0 GB
Vision
LL
Tiamat 8b 1.2 Llama 3 DPO i1
Llama · mradermacher
Params8B
Context8K
Best fitIQ2_XXS 4.0 GB
GGUF
MI
Mistral Magistral Devstral Instruct FUSED CODER Reasoning 36B
Mistral · mradermacher
Params35.8B
Context128K
Q4_K_M21.7 GB
CodingReasoning
YI
Yi 1.5 9B Chat Abliterated
Yi · mradermacher
Params8.83B
Context4K
Best fitIQ2_XS 4.0 GB
GGUF
VE
Q25 1.5B VeoLu
Veolu · bartowski
Params1.78B
Context32K
Best fitQ8_0 2.6 GB
GGUF

Other memory sizes

Keep browsing