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.
QW
Qwen3 4B 2507 abliterated
Qwen · prithivMLmods
Params4B
Context256K
Best fitBF16 9.8 GB
MI
colgrep-agent-2B
MiniCPM · lightonai
Params2.52B
Context128K
Best fitBF16 5.9 GB
QW
Huihui Qwen3.5 0.8B Abliterated
Qwen · mradermacher
Params752M
Context256K
Best fitF16 2.4 GB
SI
Signal 3.8 27B Terse Coder
Signal · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
MI
Ministral 3 8B Reasoning UNCENSORED Heretic
Mistral · mradermacher
Params8.49B
Context256K
Best fitQ6_K 8.6 GB
GR
Granite 20b Code Instruct R1.1
Granite · RichardErkhov
Params20B
Context8K
Best fitIQ4_XS 11.8 GB
RN
EssentialAI_rnj 1 Instruct
Rnj · lmstudio-community
Params8.3B
Context32K
Best fitQ8_0 10.4 GB
BA
bagel dpo 34b v0.5 i1
Bagel · mradermacher
Params34.4B
Context195K
Best fitIQ1_M 11.3 GB
QW
Qwen3 VL Embedding 2B
Qwen · mradermacher
Params1.72B
Context256K
Best fitF16 4.9 GB
QW
Qwen3.8-27B
Qwen · loscrossos
Params27.3B
Context256K
Best fitIQ2_S 11.9 GB
FA
Falcon 11B
Falcon · mradermacher
Params11.1B
Context2K
Best fitQ6_K 11.7 GB
QW
Qwen3.5 35B A3B ultra uncensored heretic
Qwen · llmfan46
Params34.7B
Context256K
Best fitIQ2_XXS 10.5 GB
PH
Phi 3 Medium 4k Instruct
Phi · bartowski
Params14B
Context4K
Best fitQ5_K_S 11.8 GB
QW
Qwen Qwen3 VL 8B Instruct Heretic
Qwen · ThalisAI
Params8.19B
Context256K
Best fitQ8_0 10.4 GB
NE
NVIDIA-Nemotron-3.5-Bolt-E4B
Nemotron · AtomicChat
Params7.52B
Context64K
Best fitQ8_0 9.9 GB
PY
Pygmalion 2 7B
Pygmalion · TheBloke
Params6.74B
Context4K
Best fitQ8_0 12.0 GB
GE
Gemma 3 4B VL It Gemini Pro Heretic Uncensored Thinking
Gemma · mradermacher
Params3.88B
Context128K
Best fitF16 9.4 GB
QW
Qwen3 VL 4B Instruct Uncensored Abliterated
Qwen · mradermacher
Params4.02B
Context256K
Best fitF16 9.8 GB
QW
Qwen3.8 9B Distill SLERP F451 Pro Writer Uncensored
Qwen · mradermacher
Params9.2B
Context256K
Best fitQ6_K 9.2 GB
DE
decider 2b
Decider · Mapika
Params1.88B
Context256K
Best fitBF16 4.7 GB
GR
Granite 4.0 H 350m
Granite · ibm-granite
Params340M
Context1024K
Best fitBF16 2.0 GB
MI
Ministral 3 8B Claude Opus Reasoning Distilled
Mistral · mradermacher
Params8.49B
Context256K
Best fitQ6_K 8.6 GB
QW
Qwen2-0.5B
Qwen · legraphista
Params494M
Context128K
Best fitBF16 1.6 GB
AB
Hy MT2 7B Abliterated Bf16
Abliterated · alexwkleung
Params7.5B
Context256K
Best fitQ8_0 9.6 GB
MU
Muse Glimmer 30B Heretic
Muse · bartowski
Params27.9B
Context128K
Best fitQ2_K 12.0 GB
QW
Qwen3.8-27B
Qwen · qtum
Params27B
Context256K
Best fitQ8_0 5.8 GB
MU
Muse Glimmer 30B Esper4
Muse · bartowski
Params27.9B
Context128K
Best fitQ2_K 12.0 GB
GE
Gemma The Writer Mighty Sword 9B
Gemma · DavidAU
Params9.2B
Context8K
Best fitQ6_K 12.0 GB
QW
Qwen2.5 Coder 7B Instruct Abliterated
Qwen · mradermacher
Params7.62B
Context32K
Best fitQ6_K 7.2 GB
DE
uncensoredai UncensoredLM DeepSeek R1 Distill Qwen 14B
DeepSeek · bartowski
Params14.2B
Context128K
Best fitQ5_K_S 11.9 GB