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
TE
TerminalHorizon 35B A3B
Terminalhorizon · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
GGUF
OL
OLMoE 1B 7B 0924 Instruct
OLMo · bartowski
Params6.9B
Context4K
Best fitIQ2_M 3.9 GB
GGUF
GR
Granite Vision 4.1 4b
Granite · ibm-granite
Params3.4B
Context128K
Best fitQ6_K 4.0 GB
Vision
FA
Fara1.5 4B
Fara · bartowski
Params4.21B
Context256K
Best fitQ3_K_M 4.0 GB
Vision
QW
Qwen3.8 Flash Next Abliterated Uncensored Turbo Brilliance 50x Reasoning Instruct GSQ RCO DFlash
Qwen · hotocooo
Params1.34B
Context256K
Best fitF32 3.8 GB
Reasoning
QW
Qwen3.8 Flash Next MTP
Qwen · drluoto
Params3.9B
Context256K
Best fitQ5_K 4.0 GB
GGUF
QW
Dongfangshuo Qwen3.8 27B NSFW v4
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
Roleplay
QW
Qwen3.8 27B Abliterated
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
GGUF
QW
Qwen3.8 14B Instruct Turbo
Qwen · mradermacher
Params14.7B
Context256K
Q4_K_M9.2 GB
ReasoningTool use
DE
DeepSeek R1 Distill Qwen 7B Uncensored
DeepSeek · mradermacher
Params7.61B
Context128K
Best fitQ2_K 4.0 GB
Reasoning
LL
ultravox v0 5 llama 3 2 1b
Llama · ggml-org
Params1.24B
Context128K
Best fitQ8_0 2.1 GB
Vision
MI
maywell Mistral ko 7B v0.1
Mistral · RichardErkhov
Params1.5B
Context—
Best fitIQ3_XS 4.0 GB
GGUF
TI
TIPO 200M Ft
Tipo · KBlueLeaf
Params203M
Context2K
Best fitF16 1.4 GB
Vision
SA
Sage A1.5 Heretic Abliterated Uncensored
Sage · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
CodingReasoningTool use
LF
LFM2 350M
Lfm · LiquidAI
Params354M
Context125K
Best fitF16 1.7 GB
GGUF
QW
Qwopus3.5 4B Coder MTP HF
Qwen · Jackrong
Params334M
Context256K
Best fitQ3_K_M 3.9 GB
CodingReasoningTool use
QW
Qwen3 235B A22B Instruct 2507
Qwen · bartowski
Params235B
Context256K
Q4_K_M142.6 GB
GGUF
QW
Dongfangshuo Qwen3.8 27B NSFW Novel
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
Roleplay
HO
Holo4 35B A3B
Holo · bartowski
Params34.7B
Context256K
Q4_K_M22.3 GB
Vision
JI
Hf Jinen v2 Small
Jinen · togatogah
Params110M
Context1K
Best fitF16 1.0 GB
GGUF
MI
Source Hf Minicpm V 4.7 1b
MiniCPM · ngquocvinh
Params1.01B
Context256K
Best fitQ8_0 2.0 GB
Vision
QW
Qwen2.5 VL 7B Abliterated Caption It
Qwen · mradermacher
Params7.62B
Context125K
Best fitQ2_K 4.0 GB
Vision
QW
Qwen3.5 4B Claude 4.6 OS Auto Variable HERETIC UNCENSORED THINKING
Qwen · mradermacher
Params4.21B
Context256K
Best fitIQ4_XS 4.0 GB
ReasoningRoleplayVision
QW
Qwen3 4B Abliterated
Qwen · mradermacher
Params4B
Context40K
Best fitIQ4_XS 4.0 GB
GGUF
MI
MiniCPM V 4.7 35B A3B Abliterated
MiniCPM · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool useVision
SP
rizzo flow
Spark · rizzoaiacademy
Params1.71B
Context1024K
Best fitQ8_0 3.5 GB
Coding
QW
Qwen3.5 27B Abliterated
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
GGUF
DO
Dots3 Note Prev
Dots · bartowski
Params280B
Context512K
Q4_K_M171.1 GB
Vision
LL
Llama 3.2 1B Instruct
Llama · hugging-quants
Params1.24B
Context128K
Best fitQ8_0 2.1 GB
GGUF
DE
DeepHat V1 7B
Deephat · mradermacher
Params7.62B
Context32K
Best fitQ2_K 4.0 GB
Coding

Other memory sizes

Keep browsing