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
QW
Qwen2.5 VL 3B Instruct
Qwen · ggml-org
Params3.09B
Context125K
Best fitQ4_K_M 2.7 GB
Vision
VI
VieNeu TTS 0.3B q4
Vieneu · pnnbao-ump
Params294M
Context4K
Best fitQ4_0 0.8 GB
GGUF
QW
Huihui Qwen3.8 Flash Next abliterated i1
Qwen · mradermacher
Params177B
Context—
Smallest0.6 GB
GGUF
BG
bge-base-en-v1.5
BGE · CompendiumLabs
Params109M
Context512
Best fitF32 1.2 GB
Embedding
QW
Qwen3.5 4B
Qwen · bartowski
Params4.33B
Context256K
Best fitQ2_K_L 4.0 GB
Vision
QW
Qwen Image 2.1
Qwen · leejet
Params7.12B
Context—
Best fitQ2_K 3.4 GB
GGUF
GR
Granite 4.2 3B BE
Granite · taronaeo
Params3.66B
Context—
Best fitQ6_K 3.9 GB
ReasoningTool use
IM
Z Image Turbo
Image · leejet
Params6.15B
Context—
Best fitQ3_K 4.0 GB
GGUF
GE
Gemma 4 E2B It
Gemma · bartowski
Params4.65B
Context128K
Best fitIQ2_M 3.7 GB
Vision
PH
Phi 4 Mini Instruct
Phi · unsloth
Params3.84B
Context128K
Best fitQ3_K_M 3.7 GB
Coding
QW
Qwen3 Reranker 0.6B
Qwen · ggml-org
Params596M
Context40K
Best fitQ8_0 2.1 GB
Embedding
GE
Gemma-3-4B-It
Gemma · unsloth
Params3.88B
Context128K
Best fitIQ4_NL 4.0 GB
Vision
TE
test model router download
Test · ggml-org
Params1M
Context2K
Best fitF16 0.5 GB
GGUF
BO
Bonsai-8B
Bonsai · prism-ml
Params8.2B
Context64K
Best fitQ1_0 2.9 GB
GGUF
QW
Qwen2.5 0.5B Instruct
Qwen · bartowski
Params494M
Context32K
Best fitF16 1.6 GB
GGUF
MI
MiniCPM V 4.7 1B
MiniCPM · openbmb
Params1.01B
Context256K
Best fitF16 2.9 GB
ReasoningTool useVision
QW
Qwen3 0.6B
Qwen · bartowski
Params752M
Context32K
Best fitBF16 2.9 GB
GGUF
EM
embeddinggemma-2
Embeddinggemma · ggml-org
Params271M
Context256K
Best fitBF16 2.7 GB
EmbeddingVision
QW
Qwen3.5-4B
Qwen · unsloth
Params4.33B
Context256K
Best fitQ3_K_M 4.0 GB
Vision
SU
Supra2 100M Instruct
Supra · SupraLabs
Params101M
Context2K
Best fitF16 0.8 GB
GGUF
DE
Deepseek-R1-Distill-Qwen-1.5B
DeepSeek · unsloth
Params1.78B
Context128K
Best fitQ8_0 2.6 GB
Reasoning
PH
Phi 4 Mini Instruct
Phi · bartowski
Params3.84B
Context128K
Best fitQ3_K_XL 4.0 GB
GGUF
QW
nl2sh 1.5b Q4 K M
Qwen · ThorOdinson246
Params1.54B
Context32K
Best fitQ4_K_M 1.7 GB
Coding
QW
Qwen3.5 0.8B Artemis
Qwen · turintech
Params752M
Context256K
Best fitQ5_K_M 1.5 GB
ReasoningTool useVision
LF
LFM2.5-350M
Lfm · LiquidAI
Params354M
Context125K
Best fitBF16 1.7 GB
GGUF
FL
FLUX.2 klein 4B
Flux · leejet
Params3.88B
Context—
Best fitQ4_0 3.3 GB
GGUF
QW
Qwen3.8 Flash Next
Qwen · bartowski
Params177B
Context256K
Best fitQ4_0 3.5 GB
Vision
MI
MiniCPM o 4 5
MiniCPM · openbmb
Params8.2B
Context40K
Best fitF16 2.9 GB
Vision
CP
CPH Community 7B
Cph · CypherTroopers
Params7B
Context—
Best fitQ4_K_M 0.5 GB
GGUF
QW
Qwen3.8 35B A3B Distill
Qwen · IsValorum
Params34.7B
Context256K
Best fitQ8_0 3.2 GB
ReasoningTool useVision

Other memory sizes

Keep browsing