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
Ternary Bonsai 27B
Qwen · prism-ml
Params3.6B
Context4K
Best fitQ4_1 2.5 GB
QW
Qwen3-4B-Instruct-2507
Qwen · unsloth
Params4B
Context256K
Best fitIQ4_XS 4.0 GB
MO
models moved
Models · ggml-org
Params34M
Context—
Best fitQ8_0 3.8 GB
QW
Qwen3.8 Flash Next Gyro abliterated Huihui
Qwen · agentionai
Params177B
Context256K
Smallest2.7 GB
QW
Qwen3.5-2B
Qwen · unsloth
Params1.88B
Context256K
Best fitQ8_K_XL 3.7 GB
QW
Qwen3-Vl-4B-Instruct
Qwen · unsloth
Params4B
Context256K
Best fitIQ4_XS 4.0 GB
QW
qwen2.5-1.5b-instruct
Qwen · Qwen
Params1.78B
Context32K
Best fitQ8_0 2.6 GB
EM
Embeddinggemma 300m
Embeddinggemma · ggml-org
Params308M
Context2K
Best fitQ8_0 1.0 GB
QW
Qwen3.8-27B-DFlash2
Qwen · z-lab
Params1.92B
Context256K
Best fitQ8_0 2.7 GB
QW
Ternary-Bonsai-2-9B-DFlash2
Qwen · prism-ml
Params2.5B
Context256K
Best fitQ8_0 3.4 GB
BI
BigBang v1
Bigbang · bartowski
Params35.5B
Context256K
Q4_K_M21.9 GB
QW
Qwen Image 2.1 Turbo
Qwen · DogukanUrker
Params7.1B
Context—
Best fitQ3_K 4.0 GB
GE
gemma-4-26B-A4B-it
Gemma · ggml-org
Params450M
Context256K
Best fitBF16 2.4 GB
QW
qwen2.5-0.5b-instruct
Qwen · Qwen
Params630M
Context32K
Q4_K_M0.5 GB
TH
Thomson 1.0 Small
Thomson · bartowski
Params34.7B
Context256K
Q4_K_M21.4 GB
GE
Gemmable 4 12B MTP
Gemma · Mia-AiLab
Params11.9B
Context256K
Q4_K_M0.3 GB
LF
LFM2.5 Audio 1.5B JP
Lfm · LiquidAI
Params190M
Context125K
Best fitF16 3.0 GB
TE
Ternary Bonsai 8B
Ternary · prism-ml
Params8.19B
Context64K
Best fitQ2_0 4.0 GB
QW
Qwen2.5 Coder 7B Instruct GGUF
Qwen · Qwen
Params15B
Context128K
Best fitQ2_K 4.0 GB
JA
Jan-v3.5-4B
Jan · janhq
Params4.4B
Context256K
Best fitQ3_K_M 4.0 GB
HY
Hy MT2 1.8B
tencent
Params1.79B
Context256K
Best fitQ8_0 2.9 GB
LF
LFM2.5 1.2B Instruct
Lfm · LiquidAI
Params1.17B
Context125K
Best fitBF16 3.9 GB
QW
Qwen3.8 27B Uncensored Cyber agentic imatrix
Qwen · cyjin-yl
Params31B
Context—
Smallest0.0 GB
LF
LFM2.5 230M
Lfm · LiquidAI
Params230M
Context125K
Best fitBF16 1.4 GB
ME
Mellum2.1-12B-A2.5B-Thinking
Mellum · JetBrains
Params12.1B
Context128K
Best fitBF16 2.7 GB
QW
Bonsai-27B-dspark
Qwen · prism-ml
Params3.6B
Context4K
Best fitQ4_1 2.4 GB
KA
KAT Coder V2.5 Dev
Kat · bartowski
Params34.7B
Context256K
Q4_K_M21.4 GB
MI
MiniCPM5 2B
MiniCPM · openbmb
Params2.52B
Context128K
Best fitQ8_0 3.5 GB
QW
Qwen3.8 27B
Qwen · bartowski
Params27.3B
Context256K
Q4_K_M17.4 GB
QW
Huihui Qwen3.8 Flash Next abliterated v2
Qwen · huihui-ai
Params177B
Context—
Smallest1.2 GB