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.
TR
Translategemma 4b It
Translategemma · mradermacher
Params3.88B
Context128K
Best fitQ4_K_S 4.0 GB
QW
Qwen3 ASR 1.7B
Qwen · ggml-org
Params2.03B
Context64K
Best fitQ8_0 3.6 GB
QW
Qwen2.5 Coder 1.5B Instruct
Qwen · bartowski
Params1.54B
Context32K
Best fitF16 3.8 GB
TE
test model stories260K
Test · ggml-org
Params—
Context—
Best fitF32 0.5 GB
GE
Gemma-4-E2B-It
Gemma · ente-ai
Params4.65B
Context128K
Best fitQ3_K_XL 4.0 GB
SM
SmolVLM2 2.2B Instruct
Smolvlm · ggml-org
Params1.81B
Context8K
Best fitQ8_0 4.0 GB
GE
Gemma 3 4b It
Gemma · bartowski
Params3.88B
Context128K
Best fitIQ4_NL 4.0 GB
QW
Qwen3.5 4B Claude 4.6 Opus Reasoning Distilled
Qwen · Jackrong
Params4.2B
Context256K
Best fitQ3_K_L 3.9 GB
GE
gemma-4-31B-it
Gemma · ggml-org
Params30.7B
Context256K
Best fitBF16 3.6 GB
QW
Huihui Qwen3.6 35B A3B Abliterated
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
LF
LFM3 Omni 2B
Lfm · LiquidAI
Params1.73B
Context125K
Best fitQ8_0 4.0 GB
SM
SmolLM3 3B
SmolLM · bartowski
Params3.08B
Context64K
Best fitQ6_K_L 3.7 GB
TI
TIPO 500M
Tipo · KBlueLeaf
Params508M
Context2K
Best fitF16 2.4 GB
QW
Huihui Qwen3 VL 4B Instruct Abliterated
Qwen · noctrex
Params4B
Context256K
Best fitIQ4_XS 4.0 GB
GE
Gemma-3N-E4B-It
Gemma · unsloth
Params6.9B
Context32K
Best fitIQ2_XXS 3.9 GB
HE
Hemmingway 1
Hemmingway · bartowski
Params27.3B
Context256K
Q4_K_M17.4 GB
LF
Lfm2.5-1.2B-Instruct
Lfm · unsloth
Params1.17B
Context125K
Best fitBF16 3.9 GB
QW
LFM2.5 2.6B
Qwen · DavidAU
Params2.7B
Context128K
Best fitIQ4_XS 4.0 GB
SE
Sentence Bert Swedish Cased
Sentence · KBLab
Params124M
Context512
Best fitBF16 1.1 GB
SM
SmolVLM 500M Instruct
Smolvlm · ggml-org
Params409M
Context8K
Best fitF16 1.7 GB
MI
Mistral-7B-Instruct-v0.3
Mistral · bartowski
Params7.25B
Context32K
Best fitIQ2_S 3.9 GB
QW
Qwen3 Coder Next
Qwen · bartowski
Params80B
Context256K
Q4_K_M48.7 GB
LL
Llama 3.2 3B Instruct
Llama · hugging-quants
Params3.21B
Context128K
Best fitQ4_K_M 3.5 GB
LF
LFM3 VL 2B
Lfm · LiquidAI
Params1.73B
Context125K
Best fitQ8_0 4.0 GB
AC
xl_regrind_v1
Acestep · mdmachine
Params4.99B
Context32K
Best fitBF16 1.9 GB
QW
Qwen3.6 35B A3B DFlash
Qwen · jcuypers
Params474M
Context256K
Best fitQ4_K_M 0.9 GB
MA
madlad400 3b mt
Madlad · google
Params2.94B
Context—
Smallest1.0 GB
FB
fblgit juanako 7b UNA
Fblgit · RichardErkhov
Params7.24B
Context—
Best fitQ3_K_S 4.0 GB
QW
Qwen3 4b Z Image Turbo AbliteratedV1
Qwen · BennyDaBall
Params4B
Context40K
Best fitQ3_K_M 3.8 GB
QW
Qwen3.8-27B-RANA-abliterated
Qwen · abliterant
Params27B
Context256K
Q4_K_M16.5 GB