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
PH
Phi 2 OmniMatrix i1
Phi · mradermacher
Params2.78B
Context2K
Best fitIQ2_XXS 4.0 GB
GGUF
NE
NeuralExperiment 7b MagicCoder v7
Neuralexperiment · mradermacher
Params7.24B
Context32K
Best fitIQ2_S 3.9 GB
Coding
QW
Onego_Osearch_Popular_Wiki_Qwen05B_V2_Merged
Qwen · onegoai
Params494M
Context32K
Best fitQ4_K_M 1.0 GB
GGUF
QW
Qwen3.5 35B A3B Abliterated
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
GGUF
QW
Qwen2.5 Coder 0.5B Instruct Gensyn Swarm tall tame panther
Qwen · 0xgr3y
Params494M
Context32K
Best fitF16 1.6 GB
Coding
QW
Qwen2.5 3B Instruct
Qwen · mradermacher
Params3.09B
Context32K
Best fitQ6_K 3.3 GB
GGUF
HE
Hermes 4.3 36B
Hermes · bartowski
Params36.2B
Context512K
Q4_K_M21.8 GB
ReasoningRoleplayTool use
GP
Gpt2 Medium
Gpt · mradermacher
Params406M
Context1K
Best fitQ4_0 1.6 GB
GGUF
LE
LensVLM 9B
Lensvlm · bartowski
Params8.95B
Context256K
Q4_K_M5.8 GB
Vision
HO
K2-Horizon-3.7B
Horizon · bartowski
Params5.06B
Context512K
Best fitIQ3_XXS 4.0 GB
GGUF
RU
RusMind 4.6.5 Momentum
Rusmind · DICPlay
Params4.65B
Context128K
Q4_K_M3.4 GB
ReasoningTool use
QW
Qwen3 4B 2507 abliterated
Qwen · prithivMLmods
Params4B
Context256K
Best fitQ3_K_L 3.9 GB
GGUF
MI
colgrep-agent-2B
MiniCPM · lightonai
Params2.52B
Context128K
Best fitQ8_0 3.5 GB
CodingTool use
QW
Huihui Qwen3.5 0.8B Abliterated
Qwen · mradermacher
Params752M
Context256K
Best fitF16 2.4 GB
ReasoningTool useVision
SI
Signal 3.8 27B Terse Coder
Signal · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
CodingReasoning
MI
Ministral 3 8B Reasoning UNCENSORED Heretic
Mistral · mradermacher
Params8.49B
Context256K
Best fitIQ1_M 3.9 GB
Reasoning
QW
Qwen3 VL Embedding 2B
Qwen · mradermacher
Params1.72B
Context256K
Best fitQ8_0 3.3 GB
EmbeddingVision
GE
Gemma 3 4B VL It Gemini Pro Heretic Uncensored Thinking
Gemma · mradermacher
Params3.88B
Context128K
Best fitQ4_K_S 4.0 GB
ReasoningVision
QW
Qwen3 VL 4B Instruct Uncensored Abliterated
Qwen · mradermacher
Params4.02B
Context256K
Best fitIQ4_XS 4.0 GB
Tool useVision
QW
Qwen3.8 9B Distill SLERP F451 Pro Writer Uncensored
Qwen · mradermacher
Params9.2B
Context256K
Q4_K_M5.8 GB
Roleplay
DE
decider 2b
Decider · Mapika
Params1.88B
Context256K
Best fitQ8_0 2.9 GB
GGUF
GR
Granite 4.0 H 350m
Granite · ibm-granite
Params340M
Context1024K
Best fitBF16 2.0 GB
GGUF
MI
Ministral 3 8B Claude Opus Reasoning Distilled
Mistral · mradermacher
Params8.49B
Context256K
Best fitIQ1_M 3.9 GB
Reasoning
QW
Qwen2-0.5B
Qwen · legraphista
Params494M
Context128K
Best fitBF16 1.6 GB
GGUF
MU
Muse Glimmer 30B Heretic
Muse · bartowski
Params27.9B
Context128K
Q4_K_M17.3 GB
Vision
QW
Qwen3.8-27B
Qwen · qtum
Params27B
Context256K
Q4_K_M17.7 GB
Vision
MU
Muse Glimmer 30B Esper4
Muse · bartowski
Params27.9B
Context128K
Q4_K_M17.3 GB
CodingReasoningVision
QW
Qwen2.5 Coder 7B Instruct Abliterated
Qwen · mradermacher
Params7.62B
Context32K
Best fitQ2_K 4.0 GB
Coding
QW
Qwen3.8 27B Cold Fusion GAIN Heretic
Qwen · mradermacher
Params26.9B
Context256K
Q4_K_M16.5 GB
ReasoningTool use
QW
ThinkingCap Qwen3.8 27B
Qwen · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
Reasoning

Other memory sizes

Keep browsing