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
HO
Holo4 35B A3B
Holo · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
GGUF
QW
Qwen3.5 4B
Qwen · dahara1
Params4.21B
Context256K
Best fitQ3_K_XL 4.0 GB
ReasoningTool useVision
MI
ANITA NEXT 24B Dolphin Mistral UNCENSORED ITA
Mistral · mradermacher
Params23.6B
Context40K
Q4_K_M14.3 GB
Reasoning
NE
NVIDIA Nemotron 3.5 Bolt E4B
Nemotron · bartowski
Params7.52B
Context64K
Q4_K_M5.2 GB
ReasoningTool useVision
QW
Swift 1.5 Qwen3.8 27b Heretic
Qwen · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
Vision
SM
SmolLM 135M
SmolLM · QuantFactory
Params135M
Context2K
Best fitQ2_K 0.8 GB
GGUF
PE
PentaCoder 9B
Pentacoder · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
CodingReasoning
EA
EAN 8B i1
Ean · mradermacher
Params8.19B
Context256K
Best fitIQ1_M 4.0 GB
Tool use
MI
MiniCPM5 1B Claude Opus Fable5 V2 Thinking heretic
MiniCPM · saidutta69
Params1.08B
Context128K
Best fitF16 2.9 GB
ReasoningRoleplayTool use
QW
Qwen3.5 122B A10B Heretic v2
Qwen · mradermacher
Params122B
Context256K
Q4_K_M74.2 GB
GGUF
MI
Mistral Nemo Inst 2407 12B Thinking Uncensored HERETIC HI Claude Opus
Mistral · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
ReasoningRoleplay
LL
Llama 3.2 3B Instruct
Llama · mradermacher
Params3.61B
Context128K
Best fitQ5_K_S 4.0 GB
GGUF
LF
LFM2.5 24B A2B Uncensored GSQ RCO
Lfm · abenzerps
Params24B
Context128K
Best fitF16 1.2 GB
ReasoningTool use
YI
01 ai Yi 6B
Yi · RichardErkhov
Params6.06B
Context4K
Best fitQ3_K 4.0 GB
GGUF
KR
Kronumos Kairos v2
Kronumos · mradermacher
Params7.6B
Context32K
Best fitQ2_K 4.0 GB
Coding
CA
Carnice V3
Carnice · bartowski
Params27.3B
Context256K
Q4_K_M17.8 GB
Tool useVision
ME
Meltemi 7B Instruct v1
Meltemi · mradermacher
Params7.48B
Context32K
Best fitIQ2_S 4.0 GB
GGUF
QW
Qwen3.8-Flash-Next-DFlash2
Qwen · incoai
Params603M
Context256K
Best fitBF16 1.9 GB
ReasoningTool use
CL
clef flash
Clef · NANI-Nithin
Params8.95B
Context256K
Best fitQ1_0 3.5 GB
GGUF
MO
Morpho 7B Distill
Morpho · mradermacher
Params7.62B
Context128K
Best fitQ2_K 4.0 GB
GGUF
FI
v6 Finch 7B HF
Finch · bartowski
Params7.64B
Context1024K
Best fitIQ2_M 3.9 GB
GGUF
AG
Agent Reflex 8B
Agent · mradermacher
Params8.19B
Context40K
Best fitIQ1_M 4.0 GB
Tool use
MI
Ministral 3 3B Reasoning UNCENSORED Heretic
Mistral · mradermacher
Params3.43B
Context256K
Best fitQ5_K_S 3.8 GB
ReasoningVision
QW
Qwen2.5 Coder 3B Instruct
Qwen · unsloth
Params3.09B
Context128K
Best fitQ6_K 3.3 GB
Coding
YI
CursorCore Yi 9B i1
Yi · mradermacher
Params8.83B
Context128K
Best fitIQ2_XS 4.0 GB
Coding
GR
Grug 27b
Grug · bartowski
Params27B
Context256K
Q4_K_M17.5 GB
ReasoningTool useVision
OR
Ornith 1.5 9B Uncensored
Ornith · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
Vision
LF
LFM2.5 24B A2B Uncensored2
Lfm · mradermacher
Params24B
Context128K
Q4_K_M14.5 GB
ReasoningTool use
MI
Mahou-1.3c-mistral-7B
Mistral · mradermacher
Params7.24B
Context32K
Best fitIQ2_S 3.9 GB
GGUF
NE
Nemotron Cascade 8B Thinking
Nemotron · bartowski
Params8.19B
Context32K
Q4_K_M5.0 GB
Reasoning

Other memory sizes

Keep browsing