GGUF models that fit in 16 GB

182247 GGUF language models have at least one quant whose estimated memory use is 16 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 4194304K tokens.

Most downloadedNewestLargestLongest contextSmallest
MI
MiniCPM V 4.7 35B A3B
MiniCPM · mradermacher
Params34.7B
Context256K
Best fitQ2_K 14.1 GB
Vision
MI
Mistral 7B Instruct v0.3
Mistral · QuantFactory
Params7.25B
Context32K
Best fitQ8_0 9.3 GB
GGUF
DE
Deepseek-Prover-V2-7B
DeepSeek · unsloth
Params6.91B
Context32K
Best fitQ8_K_XL 13.5 GB
GGUF
SP
Spark X2.6 4B LocalAI
Spark · weareapexcreators
Params4.45B
Context1024K
Best fitQ4_K_M 5.3 GB
ReasoningTool use
GE
Gemma 4 E4B
Gemma · mradermacher
Params7.52B
Context128K
Best fitQ8_0 9.9 GB
Vision
NA
VisionPsy Nano 460M GGUFs
Nanovlm · qvac
Params409M
Context8K
Q4_K_M0.3 GB
Vision
QW
Qwen 3.5 4B RP Finetune
Qwen · minas2025
Params4.2B
Context256K
Smallest4.5 GB
RoleplayVision
PR
PreciseCoder 9B
Precisecoder · mradermacher
Params8.95B
Context256K
Best fitQ6_K 8.9 GB
Coding
LL
DaringFortitude
Llama · TheBloke
Params13B
Context4K
Best fitQ4_K_M 15.1 GB
GGUF
CY
Cyberdonia 24B v8
Cyberdonia · mradermacher
Params23.6B
Context128K
Best fitQ4_K_S 15.4 GB
Roleplay
GE
gemma-2-9b-it
Gemma · lmstudio-community
Params9.24B
Context8K
Best fitQ8_0 13.1 GB
GGUF
NE
NVIDIA Nemotron 3.5 Bolt E4B 4GB DFlash
Nemotron · nvidia
Params360M
Context128K
Best fitBF16 1.4 GB
ReasoningTool use
QW
Qwen2.5 Coder 32B Instruct
Qwen · unsloth
Params32.8B
Context128K
Best fitQ2_K 15.0 GB
Coding
WI
Wicked Stuff 26B A4B v2.0 Final
Wicked · ReadyArt
Params25.2B
Context256K
Q4_K_M16.8 GB
ReasoningRoleplayTool use
QW
Qwen3.6 27B Architect Polaris2 Fable B F451 heretic
Qwen · mcgonzo
Params27B
Context256K
Best fitQ3_K_M 15.9 GB
Vision
QW
Qwen3.8-27B
Qwen · NilVoid
Params27.3B
Context256K
Best fitQ3_K_XL 16.0 GB
Vision
GR
grok oss Apollyon 8B
Grok · c4tdr0ut
Params8B
Context128K
Best fitQ8_0 10.1 GB
GGUF
QW
Huihui Qwen3 Next 80B A3B Thinking Abliterated
Qwen · mradermacher
Params80B
Context256K
Q4_K_M48.4 GB
Reasoning
LY
Lythri-7B-A4B
Lythri · Lythri
Params7.46B
Context128K
Best fitQ8_0 9.9 GB
GGUF
LL
dolphin 2.9.4 llama3.1 8b
Llama · bartowski
Params8B
Context128K
Best fitQ8_0 10.1 GB
Coding
AG
Agents A1 Uncensored MTP APEX
Agents · SC117
Params35.5B
Context256K
Smallest14.3 GB
ReasoningVision
OC
Occamy 1.0 Abliterated
Occamy · gbuzhf
Params34.7B
Context256K
Smallest14.5 GB
Vision
LL
Llama 2 13B
Llama · TheBloke
Params13B
Context4K
Best fitQ4_K_M 15.1 GB
GGUF
RW
Rwkv 6 World 7b
Rwkv · bartowski
Params7.64B
Context1024K
Best fitQ8_0 10.0 GB
GGUF
LF
LFM2.5 8B A1B Hermes Agentic Coder Abliterated v3
Lfm · DuoNeural
Params8.47B
Context125K
Best fitQ8_0 11.1 GB
CodingTool use
FI
FinanceGemma E4B
Financegemma · mradermacher
Params7.5B
Context128K
Best fitQ8_0 9.9 GB
Vision
VE
Veloxy Flash 15B
Veloxy · mradermacher
Params8.95B
Context256K
Best fitQ6_K 8.9 GB
CodingReasoningTool use
QW
qwen image 2.1
Qwen · gguf-org
Params338M
Context256K
Q4_K_M5.0 GB
Vision
FA
Falcon H1R 7B
Falcon · tiiuae
Params7.59B
Context256K
Best fitBF16 16.0 GB
GGUF
MI
MiniCPM V 4.7 35B A3B APEX I MiniPlus V2.1
MiniCPM · IsValorum
Params34.7B
Context256K
Q4_K_M0.2 GB
Vision

Other memory sizes

Keep browsing