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.
MI
Mistral Small 4 119B 2603
Mistral · bartowski
Params119B
Context1024K
Q4_K_M72.6 GB
MA
magnum v4 12b
Magnum · bartowski
Params12.2B
Context1000K
Best fitQ6_K 11.9 GB
MI
Mistral Small Instruct 2409
Mistral · mradermacher
Params22.2B
Context128K
Best fitQ3_K_S 12.0 GB
QW
Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled
Qwen · mradermacher
Params27B
Context256K
Best fitIQ2_M 12.0 GB
SP
Spark X2.6 4B
Spark · bartowski
Params4.11B
Context1024K
Best fitBF16 9.9 GB
QW
Qwen3.5-2B
Qwen · weareapexcreators
Params1.94B
Context256K
Best fitQ5_K_M 2.4 GB
ST
StartLux-Decision-v1.1-9B-AutoThink
Startlux · startlux-models
Params8.95B
Context256K
Best fitQ8_0 11.1 GB
LL
Llama 3.2 3B Instruct abliterated
Llama · QuantFactory
Params3.2B
Context128K
Best fitQ8_0 4.9 GB
QW
Qwen3.5 2B Claude 4.6 Opus Reasoning Distilled
Qwen · Jackrong
Params1.88B
Context256K
Best fitQ8_0 2.9 GB
GE
gemma 4 E4B it uncensored
Gemma · TrevorJS
Params7.5B
Context128K
Best fitQ8_0 9.9 GB
MI
MiniCPM5 2B LocalAI
MiniCPM · weareapexcreators
Params2.52B
Context128K
Best fitQ8_0 3.5 GB
NA
Nanbeige4.2 3B
Nanbeige · bartowski
Params4.17B
Context256K
Best fitBF16 9.6 GB
ST
StartLux Decision v1 9B Q8 0
Startlux · startlux-models
Params8.95B
Context256K
Best fitQ8_0 11.1 GB
WI
ehartford_wizardlm-7b-uncensored
Wizardlm · TheBloke
Params6.74B
Context2K
Best fitQ8_0 12.0 GB
QW
Qwen3 14B Claude 4.5 Opus High Reasoning Distill
Qwen · TeichAI
Params14.8B
Context40K
Best fitQ4_K_M 10.8 GB
QW
Qwen3 ASR 0.6B
Qwen · ggml-org
Params752M
Context64K
Best fitBF16 2.9 GB
LL
DarkIdol Llama 3.1 8B Instruct 1.2 Uncensored
Llama · QuantFactory
Params8B
Context128K
Best fitQ8_0 10.1 GB
LF
LFM2.5 1.2B Instruct LocalAI
Lfm · weareapexcreators
Params1.17B
Context125K
Best fitQ8_0 2.8 GB
GL
GLM 4.6V Flash
GLM · ggml-org
Params9.4B
Context128K
Best fitQ8_0 10.8 GB
QW
Atomic Chat / Qwen3.5 4B
Qwen · AtomicChat
Params4.21B
Context256K
Best fitQ8_0 6.1 GB
QW
Qwen3 1.7B
Qwen · lmstudio-community
Params2.03B
Context32K
Best fitQ8_0 3.6 GB
QW
Qwen3.5-4B
Qwen · weareapexcreators
Params4.33B
Context256K
Best fitQ4_K_M 4.4 GB
GE
Gemma 4 E2B it LocalAI
Gemma · weareapexcreators
Params7.5B
Context128K
Best fitQ5_K_M 7.4 GB
GE
Gemma 3 1b It
Gemma · bartowski
Params1B
Context32K
Best fitBF16 2.7 GB
PI
PII Tracer
Pii · perplexity-ai
Params596M
Context32K
Best fitF16 2.6 GB
MI
open-orca_mistral-7b-openorca
Mistral · TheBloke
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
QW
Qwen3.8 3.6 27B blend
Qwen · JetBrains
Params27.3B
Context256K
Best fitBF16 4.5 GB
BO
Bonsai-27B
Bonsai · weareapexcreators
Params27B
Context256K
Best fitQ1_0 6.5 GB
CH
Chandra Ocr 2
Chandra · prithivMLmods
Params4.84B
Context256K
Best fitBF16 11.3 GB
MI
MiniCPM OCR 1.0
MiniCPM · openbmb
Params752M
Context256K
Best fitF16 2.4 GB