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
Qwen3.8 27B Cold Fusion GAIN Heretic
Qwen · mradermacher
Params26.9B
Context256K
Best fitIQ2_S 12.0 GB
QW
ThinkingCap Qwen3.8 27B
Qwen · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
QW
qwen3 tts 12hz 1.7b ru stress
Qwen · sknyazev
Params142M
Context32K
Best fitF16 3.5 GB
FE
Fenrir X 26B A4B
Fenrir · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
AM
Amaretto 14B
Amaretto · mradermacher
Params13.5B
Context256K
Best fitQ5_K_M 11.5 GB
QW
Qwen3.5 4B Claude 3xMerge Jackrong UNCENSORED Heretic
Qwen · mradermacher
Params4.21B
Context256K
Best fitQ6_K 5.1 GB
GR
granite-3b-code-instruct
Granite · mradermacher
Params3.48B
Context2K
Best fitQ6_K 6.0 GB
MI
MiniCPM o 2 6
MiniCPM · openbmb
Params7.6B
Context32K
Best fitQ8_0 9.1 GB
MI
Mistral 7B Instruct v0.1
Mistral · mradermacher
Params7.24B
Context32K
Best fitQ6_K 7.5 GB
JA
japanese stablelm instruct beta 7B
Japanese · TheBloke
Params6.74B
Context4K
Best fitQ8_0 12.0 GB
MI
Mistral Nemo Instruct 2407 abliterated
Mistral · QuantFactory
Params12.2B
Context1000K
Best fitQ6_K 11.9 GB
HU
Huihui Ornith 1.5 9B Abliterated
Huihui · mradermacher
Params8.95B
Context256K
Best fitQ8_0 11.1 GB
MI
Voxtral Mini 3B 2507
Mistral · bartowski
Params4.01B
Context128K
Best fitBF16 9.5 GB
VI
Viking-33B
Viking · mradermacher
Params33B
Context4K
Best fitIQ2_XXS 11.6 GB
OP
openchat_openchat-3.5-1210
Openchat · TheBloke
Params7.24B
Context8K
Best fitQ8_0 9.3 GB
MI
MiniCPM V 4_6 Thinking
MiniCPM · openbmb
Params752M
Context256K
Best fitF16 2.4 GB
AE
AesCode 8B
Aescode · mradermacher
Params8.19B
Context256K
Best fitQ6_K 8.4 GB
JI
Jina Embeddings v5 Text Nano Text Matching
Jina · jinaai
Params212M
Context8K
Best fitF16 1.2 GB
GE
Gemma-4-E4B-Uncensored-HauhauCS-Aggressive
Gemma · kamjin
Params7.5B
Context128K
Best fitQ8_K 10.0 GB
OR
Ornith 1.0 9B
Ornith · bartowski
Params8.95B
Context256K
Best fitQ8_0 11.1 GB
LF
LFM3-VL-2B
Lfm · lmstudio-community
Params1.73B
Context125K
Best fitQ8_0 4.0 GB
LL
LLaMA Mesh
Llama · bartowski
Params8B
Context128K
Best fitQ8_0 10.1 GB
QW
Whittle Qwen 3.8 35B A3B
Qwen · mradermacher
Params35.5B
Context256K
Q4_K_M21.3 GB
MI
Ministral 3 8B Instruct 2512
Mistral · bartowski
Params8.49B
Context256K
Best fitQ8_0 10.7 GB
BG
Bge Small En v1.5
BGE · ggml-org
Params33M
Context512
Best fitQ8_0 0.7 GB
AE
AesCode 8B
Aescode · prithivMLmods
Params8.19B
Context256K
Best fitQ8_0 10.4 GB
JA
Jan-nano-128k
Jan · Menlo
Params4B
Context128K
Best fitQ8_0 6.0 GB
PH
Phi 3 mini 128k instruct
Phi · QuantFactory
Params3.82B
Context128K
Best fitQ8_0 7.8 GB
PH
Phi 3 Medium 128k Instruct
Phi · mradermacher
Params14B
Context128K
Best fitQ5_K_S 11.8 GB
DE
DeepSeek R1 Distill Qwen 7B Abliterated v2
DeepSeek · Melvin56
Params7.62B
Context128K
Best fitQ8_0 9.1 GB