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.
LF
LFM3 Audio 2B
Lfm · LiquidAI
Params1.73B
Context125K
Best fitBF16 5.6 GB
QW
Qwen3.5 Text 9B NSFW RP RolePlay
Qwen · mradermacher
Params8.95B
Context256K
Best fitQ8_0 11.1 GB
NE
NemoMix Unleashed 12B
Nemomix · bartowski
Params12.2B
Context1000K
Best fitQ6_K 11.9 GB
MU
Muse Glimmer 30B Heretic Uncensored
Muse · 0bserverx
Params28B
Context128K
Best fitQ2_K 11.6 GB
QW
Qwen2.5 Coder 3B Instruct
Qwen · bartowski
Params3.09B
Context32K
Best fitF16 7.0 GB
GL
Glm 4 9b Chat
GLM · QuantFactory
Params9.4B
Context128K
Best fitQ8_0 10.8 GB
IN
Index Translate 2B
Index · IndexTeam
Params1.94B
Context256K
Best fitF16 4.8 GB
MI
MiniCPM V 4.7 35B A3B DSpark
MiniCPM · openbmb
Params389M
Context256K
Best fitF16 1.4 GB
NE
NVIDIA Nemotron 3.5 Bolt 74B A9B 24GB LiLiCorr
Nemotron · nvidia
Params1.11B
Context256K
Smallest1.0 GB
QW
Qwen3.5 9B Claude 4.6 Opus Reasoning Distilled v2
Qwen · Jackrong
Params8.95B
Context256K
Best fitQ8_0 11.1 GB
QW
DFlash
Qwen · Alittlehammmer
Params1.73B
Context256K
Best fitBF16 4.1 GB
QW
Qwopus3.5 9B Coder MTP
Qwopus · Jackrong
Params456M
Context256K
Best fitQ8_0 11.4 GB
GE
Gemma 3 1B It GLM 4.7 Flash Heretic Uncensored Thinking
Gemma · Andycurrent
Params1B
Context32K
Best fitF16 2.7 GB
QW
Qwen2.5 14B Instruct Abliterated
Qwen · mradermacher
Params14.8B
Context32K
Best fitQ4_K_M 11.1 GB
QW
Swift 1.5 Qwen3.8 27b
Qwen · bartowski
Params27.3B
Context256K
Best fitIQ2_XS 11.8 GB
QW
Qwen3 0.6B Heretic Abliterated Uncensored
Qwen · mradermacher
Params596M
Context40K
Best fitF16 2.6 GB
QW
Qwen3.5 9b Nsfw Captioning v5
Qwen · mradermacher
Params8.95B
Context256K
Best fitQ8_0 11.1 GB
NE
Models Nvidia Nemotron Orchestrator 8B
Nemotron · MaziyarPanahi
Params8.19B
Context40K
Best fitQ6_K 8.4 GB
QW
Qwen3 0.6B Heretic Heresy Edition
Qwen · mradermacher
Params596M
Context40K
Best fitQ5_K_S 1.9 GB
LL
Llama 2 7B
Llama · TheBloke
Params6.74B
Context4K
Best fitQ8_0 12.0 GB
SM
SmolLM2 360M Instruct
SmolLM · bartowski
Params362M
Context8K
Best fitF16 1.6 GB
DI
Dirty Muse Writer v01 Uncensored Erotica NSFW i1
Dirty · mradermacher
Params9.24B
Context8K
Best fitQ6_K 10.9 GB
TR
Models Arcee Ai Trinity Mini
Trinity · MaziyarPanahi
Params26B
Context128K
Best fitQ2_K 10.7 GB
MI
Models Mistralai Ministral 3 14B Reasoning 2512
Mistral · MaziyarPanahi
Params13.5B
Context256K
Best fitQ5_K_M 11.5 GB
LL
Impish_LLAMA_4B_V2
Llama · SicariusSicariiStuff
Params4.5B
Context128K
Best fitQ8_0 6.4 GB
BE
Bespoke-Nimble-9B-v3
Bespoke · ggml-org
Params8.95B
Context256K
Best fitQ8_0 11.1 GB
QW
Models Qwen Qwen3 4B Thinking 2507
Qwen · MaziyarPanahi
Params4B
Context256K
Q4_K_M2.5 GB
QW
Abliterated
Qwen · criscar22
Params7.6B
Context32K
Best fitQ8_0 9.1 GB
NE
NeoHorse-1-4B
Neohorse · ngquocvinh
Params4.21B
Context256K
Best fitQ8_0 6.1 GB
TI
Tinylaya For Testing
Tinylaya · ggml-org
Params90M
Context8K
Best fitQ8_0 0.7 GB