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
QW
Qwepus
Qwepus · mradermacher
Params8.95B
Context1024K
Best fitQ6_K 8.9 GB
Coding
GP
gpt2 GGUF smashed
Gpt · PrunaAI
Params163M
Context1K
Best fitQ8_0 1.0 GB
GGUF
QW
Qwen3.6 27B Omnimerge v4
Qwen · ManniX-ITA
Params27B
Context256K
Best fitIQ2_S 12.0 GB
CodingReasoningVision
LL
UCCIX Llama2 13B i1
Llama · mradermacher
Params13.1B
Context4K
Best fitIQ2_M 11.7 GB
GGUF
QW
Qwen3 Reranker 8B GGUF llama cpp
Qwen · Voodisss
Params7.57B
Context40K
Best fitQ8_0 9.8 GB
Embedding
DA
daybreak kunoichi dpo 7b
Daybreak · mradermacher
Params7.24B
Context16K
Best fitQ8_0 9.4 GB
GGUF
LL
Na0s Llama 3.1 8b Pruned 4 Layers
Llama · RichardErkhov
Params6.94B
Context128K
Best fitQ8_0 8.8 GB
GGUF
RE
ReFeed 8B
Refeed · mradermacher
Params8.03B
Context128K
Best fitQ6_K 8.2 GB
Tool use
BE
Behemoth X 123B v2.2
Behemoth · mradermacher
Params123B
Context128K
Q4_K_M73.2 GB
GGUF
GE
Gemma 3 4b it MAX HORROR Uncensored DBL X Imatrix
Gemma · DavidAU
Params4.26B
Context128K
Best fitQ8_0 6.9 GB
Roleplay
IN
INTELLECT 1 Instruct
Intellect · bartowski
Params10.2B
Context8K
Best fitQ6_K_L 10.5 GB
Coding
GR
granite-8b-code-instruct
Granite · ibm-granite
Params8.05B
Context4K
Best fitQ4_K_M 6.6 GB
CodingTool use
TI
Tinyllama-Cinder-1.3B-Reason-Test
Tinyllama · RichardErkhov
Params1.28B
Context2K
Best fitQ8_0 2.1 GB
GGUF
SM
SmolLM2 360M
SmolLM · QuantFactory
Params362M
Context8K
Best fitQ6_K 1.2 GB
GGUF
DA
MN Dark Horror The Cliffhanger 18.5B
Dark · DavidAU
Params18.5B
Context1000K
Best fitQ3_K_M 11.7 GB
Roleplay
PH
Phi 3 mini 128k instruct imatrix
Phi · duyntnet
Params3.82B
Context128K
Best fitQ8_0 7.8 GB
GGUF
MI
llava v1.6 mistral 7b
Mistral · mradermacher
Params7.24B
Context32K
Best fitQ8_0 9.4 GB
Vision
LL
Llama 3.2 1B Instruct Abliterated
Llama · mradermacher
Params1.5B
Context128K
Best fitF16 3.8 GB
GGUF
MU
Muse Glimmer 30B Uncensored Heretic
Muse · mradermacher
Params27.9B
Context128K
Best fitQ2_K 11.6 GB
Vision
MI
Ministral-3-8B-Reasoning-2512
Mistral · Mungert
Params8.5B
Context256K
Best fitQ8_0 10.7 GB
Reasoning
TE
Ternary Bonsai 2 27B Abliterated PTQ1 0 MTP Q4 0
Ternary · Cheurteen
Params26.9B
Context256K
Best fitQ5_0 8.9 GB
ReasoningTool use
SP
Spark X2.5 4B
Spark · mradermacher
Params4.11B
Context1024K
Best fitQ6_K 5.1 GB
GGUF
LF
Lfm2-8B-A1B
Lfm · unsloth
Params8.34B
Context125K
Best fitQ8_K_XL 11.1 GB
GGUF
QW
Qwen3.5 9B Claude Code
Qwen · empero-ai
Params8.95B
Context256K
Best fitQ8_0 11.1 GB
Coding
MI
Young Children Storyteller Mistral 7B
Mistral · RichardErkhov
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
GGUF
QW
Qwen3 Coder 30B A3B IT Heretic
Qwen · mradermacher
Params30.5B
Context256K
Best fitQ2_K_S 11.8 GB
Coding
HE
Hemmingway 1.5
Hemmingway · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
ReasoningTool use
HO
K2-Horizon-3.7B
Horizon · mradermacher
Params5.06B
Context512K
Best fitQ6_K 5.9 GB
GGUF
PH
Phi 3.5 Mini 3.8B ArliAI RPMax v1.1
Phi · bartowski
Params3.82B
Context128K
Best fitF16 11.4 GB
GGUF
QW
Qwen3.8 2B Heretic
Qwen · mradermacher
Params1.88B
Context256K
Best fitQ6_K 2.5 GB
ReasoningTool use

Other memory sizes

Keep browsing