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
Qwen3.6 35B A3B
Qwen · bartowski
Params35.5B
Context256K
Best fitQ8_0 3.2 GB
LL
Llama 3.2 3B Instruct
Llama · bartowski
Params3.21B
Context128K
Best fitQ5_K_L 3.9 GB
LA
Laguna S 2.1 APEX
Laguna · Myric
Params118B
Context1024K
Best fitQ8_0 1.9 GB
GE
gemma 4 26B A4B it qat
Gemma · unsloth
Params430M
Context128K
Best fitBF16 2.4 GB
QW
Qwen3 1.7B Instruct
Qwen · Qwen
Params1.72B
Context40K
Best fitQ8_0 3.3 GB
GR
Parable Granite 4.1 3B Claude Fable 5
Granite · AnkitAI
Params3.4B
Context128K
Best fitQ6_K 4.0 GB
LL
Llama-3.2-3B-Instruct
Llama · unsloth
Params3.21B
Context128K
Best fitQ5_K_M 3.8 GB
QW
Qwen3.8 Flash Next Uncensored i1
Qwen · mradermacher
Params177B
Context—
Smallest0.6 GB
GE
gemma-4-E2B-it
Gemma · ggml-org
Params4.65B
Context128K
Best fitQ4_0 3.4 GB
BG
bge-small-en-v1.5
BGE · CompendiumLabs
Params33M
Context512
Best fitF32 0.8 GB
QW
Holo 3.1 35B A3B
Qwen · Hcompany
Params34.7B
Context256K
Q4_K_M21.3 GB
QW
Qwen3 Embedding 0.6b
Qwen · Qwen
Params596M
Context32K
Best fitF16 2.6 GB
HO
Diplodocus preview 4
Horizon · OsaurusAI
Params9B
Context512K
Q4_K_M6.3 GB
DE
Deepseek-R1-0528-Qwen3-8B
DeepSeek · unsloth
Params8.19B
Context128K
Best fitIQ1_S 4.0 GB
QW
Qwen3.8 27B Uncensored
Qwen · bartowski
Params27.3B
Context256K
Q4_K_M17.8 GB
LL
Llama 3.2 1B Instruct
Llama · bartowski
Params1.24B
Context128K
Best fitF16 3.2 GB
AL
all-MiniLM-L6-v2
All · second-state
Params23M
Context512
Best fitQ2_K 0.6 GB
QW
Qwen3-0.6B
Qwen · unsloth
Params596M
Context40K
Best fitBF16 2.6 GB
QW
Qwen3 4B
Qwen · bartowski
Params4B
Context32K
Best fitIQ4_XS 4.0 GB
AL
all-MiniLM-L6-v2
All · leliuga
Params23M
Context512
Best fitF32 0.7 GB
EM
Embeddinggemma 2
Embeddinggemma · unsloth
Params271M
Context256K
Best fitBF16 2.7 GB
GE
gemma-4-E4B-it
Gemma · ggml-org
Params7.5B
Context128K
Best fitBF16 0.8 GB
TA
UI-TARS-1.5-7B
Tars · Mungert
Params7.6B
Context125K
Best fitIQ2_M 4.0 GB
QW
Qwen3-8B
Qwen · unsloth
Params8.19B
Context40K
Best fitIQ1_S 4.0 GB
GE
gemma 4 E4B it qat
Gemma · unsloth
Params93M
Context128K
Best fitQ2_K_XL 3.9 GB
QW
Qwen3.6-35B-A3B
Qwen · ggml-org
Params1.9B
Context256K
Best fitQ8_0 3.2 GB
SN
snowflake arctic embed m v1.5
Snowflake · Snowflake
Params109M
Context512
Best fitF32 1.2 GB
DE
DeepSeek R1 Distill Qwen 7B
DeepSeek · bartowski
Params7.62B
Context128K
Best fitQ2_K 4.0 GB
BG
bge-large-en-v1.5
BGE · CompendiumLabs
Params334M
Context512
Best fitF32 2.6 GB
QW
Qwen3 1.7B
Qwen · ggml-org
Params2.03B
Context40K
Best fitQ8_0 3.6 GB