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
RO
RoMistral-7b-Instruct
Romistral · legraphista
Params7.24B
Context32K
Best fitIQ2_S 3.9 GB
GGUF
QW
Dongfangshuo Qwen3.8 27B NSFW
Qwen · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
RoleplayVision
YI
Yi 6B Chat
Yi · RichardErkhov
Params6.06B
Context4K
Best fitQ3_K 4.0 GB
GGUF
MI
Abliterated Dolphin3.0 R1 Mistral 24B
Mistral · mradermacher
Params23.6B
Context32K
Q4_K_M14.3 GB
Reasoning
QW
Qwen3.5 9B The Defiant Fable DARK ROAST Uncensored Heretic NEO IMATRIX MAX MTP
Qwen · mradermacher
Params9.2B
Context256K
Q4_K_M5.8 GB
CodingReasoningRoleplay
LF
LFM2.5 Embedding 350M
Lfm · LiquidAI
Params354M
Context125K
Best fitBF16 1.7 GB
Embedding
JA
Jan-Nano-128K
Jan · unsloth
Params4B
Context128K
Best fitIQ4_XS 4.0 GB
GGUF
QW
Ingot 27B DFlash2
Qwen · dendriteholdings
Params1.92B
Context256K
Best fitQ8_0 2.7 GB
ReasoningTool use
QW
Qwen3.8 27B Med Ablit Heretic
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
GGUF
LL
turboderp Cat Llama 3 70B instruct
Llama · RichardErkhov
Params3.3B
Context—
Best fitIQ3_M 2.2 GB
GGUF
QW
Qwen3.8 27B Max Ablit Heretic
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
GGUF
GR
Granite-4.0-H-Micro
Granite · unsloth
Params3.2B
Context1024K
Best fitIQ1_S 4.0 GB
GGUF
AB
ABD3ID CodeMentor
Abd · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
Coding
DE
DeepSeek R1 Distill Qwen 1.5B
DeepSeek · lmstudio-community
Params1.78B
Context128K
Best fitQ8_0 2.6 GB
Reasoning
DE
deepseek-ai_deepseek-coder-5.7bmqa-base
DeepSeek · TheBloke
Params5.7B
Context16K
Best fitQ4_0 3.9 GB
Coding
CO
Cotype Nano
Cotype · QuantFactory
Params1.54B
Context32K
Best fitQ8_0 2.4 GB
GGUF
QW
Swift Qwen3.8 Flash Next
Qwen · bartowski
Params177B
Context256K
Q4_K_M125.6 GB
ReasoningVision
QW
cerebras/Qwen3-Coder-REAP-25B-A3B
Qwen · bartowski
Params25B
Context256K
Q4_K_M15.2 GB
Coding
PA
PaddleOCR VL manga
Paddleocr · LunarOilRig
Params467M
Context128K
Best fitQ4_K_M 1.0 GB
Vision
LL
Llama-3-ELYZA-JP-8B
Llama · mmnga
Params8B
Context8K
Best fitIQ2_XXS 4.0 GB
GGUF
AN
Anubis 70B v1.2
Anubis · bartowski
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
QW
Huihui Qwen3 Next 80B A3B Instruct Abliterated
Qwen · mradermacher
Params80B
Context256K
Q4_K_M48.4 GB
GGUF
QW
ThinkingCap Qwen3.6 27B abliterated MTP
Qwen · protoLabsAI
Params27.3B
Context—
Best fitQ8_0 4.0 GB
Reasoning
FI
Finch 3b
Finch · latestissue
Params3.1B
Context1024K
Best fitQ6_K 3.4 GB
GGUF
QW
Agnes 3.0 Qwen
Qwen · bartowski
Params180B
Context1024K
Q4_K_M127.1 GB
ReasoningTool useVision
LI
LightOnOCR 3 1B
Lightonocr · prithivMLmods
Params596M
Context16K
Best fitBF16 2.6 GB
Vision
LL
Llama 3.1 Swallow 8B Instruct v0.5
Llama · mmnga
Params8B
Context128K
Best fitIQ2_XXS 4.0 GB
GGUF
QW
Qwen2.5 Vl 7b Cam Motion
Qwen · mradermacher
Params7.62B
Context125K
Best fitQ2_K 4.0 GB
Vision
QW
Irwan LightOnOCR 3 0.8B Abliterated
Qwen · irwanworld
Params752M
Context256K
Best fitQ8_0 1.7 GB
ReasoningTool useVision
QW
Qwen3 4B Instruct 2507 Heretic
Qwen · bartowski
Params4B
Context256K
Best fitIQ4_XS 4.0 GB
GGUF

Other memory sizes

Keep browsing