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
QW
Qwen2.5 Coder 3B
Qwen · lmstudio-community
Params3.09B
Context32K
Best fitQ6_K 3.3 GB
Coding
GE
Gemma 4 26B A4B It Assistant
Gemma · AtomicChat
Params420M
Context256K
Best fitF16 2.4 GB
GGUF
QW
Qwen2.5-3B-Instruct
Qwen · Mungert
Params3.1B
Context32K
Best fitBF16 3.7 GB
GGUF
LL
Llama Leonida v2
Llama · mradermacher
Params8.2B
Context128K
Best fitIQ1_M 3.8 GB
GGUF
ZE
zenz v3.2 small
Zenz · Miwa-Keita
Params95M
Context1K
Best fitQ5_K_M 0.9 GB
GGUF
SZ
SzilviaB Daredevil LongWriter 8B abliterated i1
Szilviab · mradermacher
Params8B
Context8K
Best fitIQ2_XXS 4.0 GB
GGUF
QW
Qwen3 32B VL Instruct Polaris HI16 Heretic Uncensored
Qwen · mradermacher
Params32.8B
Context256K
Q4_K_M19.8 GB
RoleplayVision
MI
Mahou-1.2-mistral-7B
Mistral · mradermacher
Params7.24B
Context32K
Best fitIQ2_S 3.9 GB
GGUF
QW
RA RFT Qwen2.5 VL 7B
Qwen · mradermacher
Params7.62B
Context125K
Best fitQ2_K 4.0 GB
Vision
LF
LFM2.5 350M RLCD
Lfm · NANI-Nithin
Params354M
Context125K
Best fitBF16 1.7 GB
GGUF
TI
Tinystories-gpt-0.1-3m
Tinystories · afrideva
Params7M
Context2K
Best fitQ2_K 0.5 GB
GGUF
QW
online-dpo-qwen2-4
Qwen · RichardErkhov
Params494M
Context32K
Best fitQ6_K 1.1 GB
GGUF
QW
hamo score 0.6b
Qwen · HamoAI
Params596M
Context40K
Smallest0.6 GB
GGUF
GE
Gemma-3N-E4B-It
Gemma · unsloth
Params6.9B
Context32K
Best fitIQ2_XXS 3.9 GB
Vision
QW
ColdBrew Qwen3.5 CharThink Base
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool use
LL
Vikhr-Llama-3.2-1B-instruct
Llama · Vikhrmodels
Params1.24B
Context128K
Best fitF16 3.2 GB
GGUF
QW
RuntimeLabs Kayak Qwen3 VL 4B
Qwen · mradermacher
Params4B
Context256K
Best fitIQ4_XS 4.0 GB
Vision
GT
gte-large
Gte · opaninakuffo
Params334M
Context512
Smallest0.7 GB
GGUF
GE
Octopus-v2
Gemma · NexaAI
Params2.51B
Context8K
Best fitQ8_0 3.3 GB
GGUF
QW
Qwen3 Embedding 0.6B
Qwen · PeterAM4
Params596M
Context32K
Best fitBF16 2.6 GB
Embedding
CO
ContextualKunoichi KTO 7B i1
Contextualkunoichi · mradermacher
Params7.24B
Context32K
Best fitIQ2_S 3.9 GB
GGUF
QW
Qwen2 0.5B NuminaMath TIR v1
Qwen · mradermacher
Params494M
Context32K
Best fitF16 1.6 GB
GGUF
ST
stabilityai japanese stablelm base beta 70b
Stabilityai · RichardErkhov
Params1.6B
Context—
Best fitIQ3_M 1.3 GB
GGUF
DE
DeepHat V1 7B imatrix
Deephat · liodon-ai
Params7.62B
Context32K
Best fitIQ2_M 3.8 GB
Coding
ZE
zephyr 7b hh dpo i1
Zephyr · mradermacher
Params7.24B
Context32K
Best fitIQ2_S 3.9 GB
GGUF
ST
starcoder2-7b
StarCoder · second-state
Params7.17B
Context16K
Best fitQ2_K 3.8 GB
Coding
AP
Apriel 1.5 15b Thinker
Apriel · mradermacher
Params14.4B
Context256K
Q4_K_M8.8 GB
ReasoningVision
QW
Qwen3.5 2B
Qwen · SoAIHQ
Params1.94B
Context256K
Best fitQ8_0 3.0 GB
ReasoningTool useVision
LL
lightblue suzume llama 3 8B japanese
Llama · mmnga
Params8B
Context8K
Best fitIQ2_XXS 4.0 GB
GGUF
QW
Qwen2.5 Wolverine CODER 11B V2 128k Ctx
Qwen · mradermacher
Params10.9B
Context128K
Best fitIQ1_M 4.0 GB
Coding

Other memory sizes

Keep browsing