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.
IN
INTELLECT 3
Intellect · bartowski
Params107B
Context128K
Q4_K_M71.4 GB
EM
embeddinggemma-2
Embeddinggemma · AtomicChat
Params271M
Context256K
Best fitBF16 2.7 GB
EM
Embeddinggemma 300M Qat Q4_0 Unquantized
Embeddinggemma · ggml-org
Params303M
Context2K
Best fitQ4_0 1.0 GB
QW
Qwen3.5 4B Heretic 2xMerge DavidAU
Qwen · mradermacher
Params4.21B
Context256K
Best fitQ3_K_L 4.0 GB
OR
Ornith 1.5 27B A3B CoderX MTP
Ornith · ManniX-ITA
Params26.2B
Context256K
Q4_K_M16.1 GB
JI
jina embeddings v2 base code
Jina · second-state
Params160M
Context8K
Best fitF16 1.1 GB
LL
Hermes 3 Llama 3.1 8B
Llama · legraphista
Params8B
Context128K
Best fitIQ2_XXS 4.0 GB
LL
Hermes 3 Llama 3.1 8B
Llama · mradermacher
Params8B
Context128K
Best fitIQ2_XXS 4.0 GB
GE
Gemma 3 4b It
Gemma · DavidAU
Params3.88B
Context128K
Best fitIQ2_S 4.0 GB
TI
Tiny Aya Global
Tiny · CohereLabs
Params3.35B
Context488K
Best fitQ4_K_M 3.2 GB
HO
K2 Horizon 7B
Horizon · NANI-Nithin
Params9B
Context512K
Best fitQ1_0 3.7 GB
OX
OxCoder 9B GMCE
Oxcoder · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
UM
umiyuki Japanese Chat Umievo itr001 7b
Umiyuki · mmnga
Params7.24B
Context4K
Best fitIQ2_S 3.9 GB
GE
Gemmasutra Mini 2B v1
Gemma · l3utterfly
Params2.61B
Context8K
Best fitQ6_K 3.5 GB
ME
Melody1437 35B A3B
Melody · ReadyArt
Params35.5B
Context256K
Q4_K_M21.7 GB
DE
DeepSeek R1 Distill Qwen 1.5B Abliterated
DeepSeek · mradermacher
Params1.78B
Context128K
Best fitQ8_0 2.6 GB
LL
Llama3.2 DeepHermes 3 3B Preview Reasoning MAX NEO Imatrix
Llama · DavidAU
Params3.21B
Context128K
Best fitQ4_K_M 3.9 GB
GR
Granite Speech 5.0 2b
Granite · ibm-granite
Params1.84B
Context16K
Best fitQ8_0 3.1 GB
IC
IceTea21EnergyDrinkRPV13 DPOv3 i1
Icetea · mradermacher
Params7.24B
Context32K
Best fitIQ2_S 3.9 GB
QW
ThinkingCap Qwen3.6 27B
Qwen · bartowski
Params27.3B
Context256K
Q4_K_M17.8 GB
QW
Qwepus
Qwepus · mradermacher
Params8.95B
Context1024K
Q4_K_M5.6 GB
GP
gpt2 GGUF smashed
Gpt · PrunaAI
Params163M
Context1K
Best fitQ8_0 1.0 GB
LL
Na0s Llama 3.1 8b Pruned 4 Layers
Llama · RichardErkhov
Params6.94B
Context128K
Best fitQ4_0 3.2 GB
RE
ReFeed 8B
Refeed · mradermacher
Params8.03B
Context128K
Best fitIQ2_XXS 4.0 GB
BE
Behemoth X 123B v2.2
Behemoth · mradermacher
Params123B
Context128K
Q4_K_M73.2 GB
GE
Gemma 3 4b it MAX HORROR Uncensored DBL X Imatrix
Gemma · DavidAU
Params4.26B
Context128K
Best fitIQ1_S 3.9 GB
TI
Tinyllama-Cinder-1.3B-Reason-Test
Tinyllama · RichardErkhov
Params1.28B
Context2K
Best fitQ8_0 2.1 GB
SM
SmolLM2 360M
SmolLM · QuantFactory
Params362M
Context8K
Best fitQ6_K 1.2 GB
LL
Llama 3.2 1B Instruct Abliterated
Llama · mradermacher
Params1.5B
Context128K
Best fitF16 3.8 GB
MI
Ministral-3-8B-Reasoning-2512
Mistral · Mungert
Params8.5B
Context256K
Q4_K_M5.5 GB