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
ST
Storm-7B
Storm · mradermacher
Params7.24B
Context8K
Best fitIQ2_S 3.9 GB
GGUF
AC
AceInstruct 7B
Aceinstruct · bartowski
Params7.62B
Context128K
Best fitQ2_K 4.0 GB
Coding
PH
Phind 70B
Phind · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
Coding
KI
Kimi K2.5
Kimi · bartowski
Params1030B
Context256K
Q4_K_M580.4 GB
Vision
LL
llama-3-8b-samantha
Llama · mradermacher
Params8B
Context8K
Best fitIQ2_XXS 4.0 GB
GGUF
CO
CodeQwen1.5-7B
Codeqwen · bartowski
Params7.25B
Context64K
Best fitIQ2_M 4.0 GB
GGUF
JI
Jina Embeddings v5 Text Nano Clustering
Jina · jinaai
Params212M
Context8K
Best fitF16 1.2 GB
CodingEmbedding
BL
BlackMagic-7B
Blackmagic · mradermacher
Params7.24B
Context8K
Best fitIQ2_S 3.9 GB
GGUF
PY
Pythia 1b
Pythia · mradermacher
Params1.01B
Context2K
Best fitF16 3.6 GB
GGUF
QW
Qwen2.5 Coder 1.5B Instruct
Qwen · ggml-org
Params1.54B
Context32K
Best fitQ8_0 2.4 GB
Coding
QW
Qwen2.5 Furry 7B
Qwen · mradermacher
Params7.62B
Context128K
Best fitQ2_K 4.0 GB
Roleplay
QW
Qwen3.8 27B DSpark
Qwen · Anbeeld
Params1.86B
Context256K
Best fitQ8_0 2.7 GB
CodingEmbedding
QW
Haru Qwen3 4b
Qwen · mradermacher
Params4B
Context256K
Best fitIQ4_XS 4.0 GB
Roleplay
MI
ANIMA Cognitive Mistral v1 i1
Mistral · mradermacher
Params7.24B
Context32K
Best fitIQ2_S 3.9 GB
GGUF
GL
LFM2 12B A1B GLM 4.7 Thinking Quantum IQ1C P TR1 S2
GLM · mradermacher
Params11.3B
Context125K
Q4_K_M6.8 GB
CodingReasoningRoleplay
ST
Starcoder2 7b
StarCoder · QuantFactory
Params7.17B
Context16K
Best fitQ2_K 3.9 GB
Coding
ME
Merlin Agent
Merlin · bartowski
Params8.95B
Context256K
Q4_K_M5.9 GB
Coding
OR
Orpheus 3b 0.1 Pretrained GGUF
Orpheus · HorizonNexusAI
Params3.3B
Context128K
Best fitQ5_K_M 3.8 GB
GGUF
CO
Codeqwen3 14b
Codeqwen · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
CodingReasoning
QW
OPSD Qwen3 8B
Qwen · mradermacher
Params8.19B
Context40K
Best fitIQ1_M 4.0 GB
ReasoningTool use
OP
OpenELM-270M-Instruct
Openelm · RichardErkhov
Params272M
Context2K
Best fitQ6_K 0.8 GB
GGUF
RA
RakutenAI 7B
Rakutenai · mradermacher
Params7.37B
Context32K
Best fitIQ2_S 4.0 GB
GGUF
IN
Internvl3-8B
Internvl · unsloth
Params7.61B
Context32K
Best fitQ2_K 4.0 GB
CodingVision
TI
TigerCoder 12B
Tigercoder · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
Coding
PR
PromptEnhancer 32B
Promptenhancer · mradermacher
Params32.8B
Context125K
Q4_K_M19.9 GB
GGUF
QW
X Coder SFT Qwen3 8B
Qwen · mradermacher
Params8.19B
Context32K
Best fitIQ1_M 4.0 GB
Coding
QW
Qwen3.5 0.8B Heretic
Qwen · saidutta69
Params752M
Context256K
Best fitF16 2.4 GB
ReasoningTool use
LL
Llama-3-Mopeyfied-Psychology-v2
Llama · mradermacher
Params8.03B
Context8K
Best fitIQ2_XXS 4.0 GB
GGUF
LL
llama3-8B-DarkIdol-2.1-Uncensored-1048K
Llama · mradermacher
Params8B
Context1024K
Best fitIQ2_XXS 4.0 GB
Roleplay
QW
qwen2.5 coder 32b combined verilog c i1
Qwen · mradermacher
Params32.8B
Context32K
Q4_K_M19.8 GB
Coding

Other memory sizes

Keep browsing