GGUF models that fit in 12 GB

171517 GGUF language models have at least one quant whose estimated memory use is 12 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
LL
Llama-3.1-Nemotron-Nano-8B-V1
Llama · unsloth
Params8B
Context128K
Best fitQ6_K_XL 8.9 GB
GGUF
QW
Qwen3.5 9B The Defiant Fable Uncensored Heretic NEO IMATRIX MAX MTP
Qwen · zugquants
Params8.95B
Context256K
Best fitQ6_K 10.3 GB
CodingReasoningRoleplay
AI
jondurbin_airoboros-m-7b-3.1.2
Airoboros · TheBloke
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
GGUF
ME
Med Advisor Conversation 4B
Med · mradermacher
Params4.41B
Context40K
Best fitQ6_K 5.3 GB
ReasoningTool use
ST
L3 8B Stheno v3.1
Stheno · QuantFactory
Params8B
Context8K
Best fitQ8_0 10.1 GB
GGUF
MA
Magnum 12b v2.5 Kto
Magnum · bartowski
Params12.2B
Context1000K
Best fitQ6_K 11.9 GB
GGUF
GP
GPT OSS Swallow 120B RL v0.1
gpt-oss · mradermacher
Params117B
Context128K
Q4_K_M87.9 GB
CodingTool use
JA
Jais adapted 7B Reflection Tuning Natural Farmer i1
Jais · mradermacher
Params7B
Context4K
Best fitQ6_K 10.5 GB
GGUF
OR
Orion 26B A4B v1.1
Orion · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
GGUF
NX
Nxcode-CQ-7B-orpo
Nxcode · legraphista
Params7.25B
Context64K
Best fitQ8_0 8.7 GB
Coding
GE
Security SLM Gemma 4 E2B it
Gemma · entrick
Params4.65B
Context128K
Best fitQ4_K_M 4.5 GB
Tool use
QW
Huihui Qwen3.5 35B A3B Claude 4.6 Opus Abliterated
Qwen · mradermacher
Params34.7B
Context256K
Best fitIQ2_S 11.8 GB
Reasoning
NE
Nemotron 3.5 Bolt 74B A9B CRACK 24GB
Nemotron · dealignai
Params74B
Context256K
Smallest1.0 GB
Vision
CO
Yi Coder 1.5B Chat
Coder · mradermacher
Params1.48B
Context128K
Best fitQ6_K 3.4 GB
Coding
BG
bge m3
BGE · CompendiumLabs
Params567M
Context8K
Best fitF32 3.6 GB
Embedding
MI
Mahou-1.3-mistral-7B
Mistral · mradermacher
Params7.24B
Context32K
Best fitQ6_K 7.5 GB
GGUF
MI
MiniCPM V 4.7 1B
MiniCPM · mradermacher
Params1.01B
Context256K
Best fitQ6_K 1.8 GB
Vision
MI
Mistral Medium 3.5 128B
Mistral · bartowski
Params125B
Context256K
Q4_K_M78.4 GB
Vision
QW
Qwen3 VL 8B Instruct
Qwen · mradermacher
Params8.19B
Context256K
Best fitQ6_K 8.4 GB
Vision
DE
Q3 30B A3B Designant
Designant · bartowski
Params30.5B
Context32K
Best fitIQ2_M 11.5 GB
ReasoningRoleplay
GE
Gemma 3 4b It Heretic Uncensored Abliterated Extreme
Gemma · mradermacher
Params3.88B
Context128K
Best fitF16 9.4 GB
Vision
QW
Qwen3 8B Heretic GGUF
Qwen · xFanexx
Params8.19B
Context40K
Best fitQ8_0 10.4 GB
GGUF
ST
stable-code-3b
Stable · mradermacher
Params2.8B
Context16K
Best fitQ6_K 5.5 GB
Coding
LI
LightOnOCR 3 0.8B
Lightonocr · mradermacher
Params752M
Context256K
Best fitQ5_K_S 1.5 GB
Vision
HE
Hemmingway 1.5
Hemmingway · bartowski
Params27.3B
Context256K
Best fitIQ2_XS 11.8 GB
ReasoningTool use
OC
Occamy 1.0 APEX I NanoPlus
Occamy · IsValorum
Params34.7B
Context256K
Best fitQ8_0 3.2 GB
ReasoningTool useVision
BE
BetterWright K2 Horizon 7B Uno
Betterwright · mradermacher
Params9B
Context512K
Best fitQ6_K 9.1 GB
Tool use
QW
Qwen2.5 Coder 3B Instruct
Qwen · unsloth
Params3.09B
Context32K
Best fitF16 7.0 GB
Coding
GE
Gemma 4 Vain 26B A4B
Gemma · Ozili
Params25.2B
Context256K
Q4_K_M16.8 GB
ReasoningRoleplayTool use
GE
Gemma 4 19B A4B It INSTRUCT Heretic Uncensored
Gemma · mradermacher
Params18.4B
Context256K
Q4_K_M12.3 GB
CodingRoleplay

Other memory sizes

Keep browsing