GGUF models that fit in 32 GB
198257 GGUF language models have at least one quant whose estimated memory use is 32 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-Vl-8B-Thinking
Qwen · unsloth
Params8.19B
Context256K
Best fitBF16 18.1 GB
QW
Qwen3 VL 2B Instruct
Qwen · bartowski
Params1.72B
Context256K
Best fitBF16 4.9 GB
GE
Gemma 4 E2B It Heretic v1
Gemma · mradermacher
Params4.63B
Context128K
Best fitQ6_K 4.9 GB
QW
Qwen3.5 397B A17B
Qwen · bartowski
Params403B
Context256K
Best fitQ8_0 10.7 GB
VE
Veloxy Titan 32B Vision
Veloxy · mradermacher
Params26.9B
Context256K
Best fitQ6_K 24.7 GB
ON
OneJev 9B
Onejev · bartowski
Params8.95B
Context256K
Best fitBF16 19.5 GB
PA
Pantheon Reasoning 26B A4B 1.1 V2
Pantheon · bartowski
Params26B
Context256K
Best fitQ5_K_M 29.3 GB
QW
Qwen3 Reranker 0.6B GGUF llama cpp
Qwen · Voodisss
Params596M
Context40K
Best fitF16 2.6 GB
GR
GRM 2.6 Plus
Grm · morikomorizz
Params27B
Context256K
Best fitQ8_0 31.2 GB
OR
Ornith 1.0 35B
Ornith · bartowski
Params34.7B
Context256K
Best fitQ6_K_L 31.5 GB
HU
Huihui4 8B A4B
Huihui · huihui-ai
Params8.1B
Context256K
Best fitF16 24.8 GB
PR
Privacy Filter Multilingual
Privacy · LocalAI-io
Params1.4B
Context128K
Best fitF16 3.4 GB
BG
bge m3
BGE · lm-kit
Params567M
Context8K
Best fitF16 2.5 GB
QW
Qwen2.5 Coder 7B Instruct
Qwen · unsloth
Params7.62B
Context128K
Best fitF16 16.2 GB
QW
Qwen.Qwen3 VL Embedding 2B
Qwen · DevQuasar
Params1.72B
Context256K
Best fitF16 4.9 GB
QW
Josiefied Qwen3 8B Abliterated v1
Qwen · bartowski
Params8.19B
Context40K
Best fitBF16 18.1 GB
PH
Phi 3 mini 128k instruct GGUF Imatrix smashed
Phi · PrunaAI
Params3.82B
Context128K
Best fitQ8_0 7.8 GB
QW
Qwen3.8 27B OBLITERATED Mythos Class Agentic
Qwen · mradermacher
Params27.3B
Context256K
Best fitQ8_0 31.7 GB
AI
Airoboros L2 7B 2.1
Airoboros · TheBloke
Params6.74B
Context4K
Best fitQ8_0 12.0 GB
CY
CyberSecQwen 4B
Cybersecqwen · mradermacher
Params4B
Context256K
Best fitF16 9.8 GB
QW
Qwen3.6 35B A3B APEX MTP
Qwen · mudler
Params35.5B
Context256K
Smallest11.7 GB
LL
codellama_codellama-7b-hf
Llama · TheBloke
Params6.74B
Context16K
Best fitQ8_0 12.0 GB
PH
gretelai Phi 3 mini 128k instruct
Phi · RichardErkhov
Params1.9B
Context—
Best fitQ2_K 1.3 GB
AR
AREX 2
Arex · mradermacher
Params27B
Context256K
Best fitQ8_0 31.2 GB
QW
Huihui Qwen3 VL 30B A3B Instruct Abliterated
Qwen · mradermacher
Params30.5B
Context256K
Best fitQ6_K 26.4 GB
QW
Qwen3.5 9B Claude 4.6 OS Auto Variable HERETIC UNCENSORED THINKING MAX NEOCODE Imatrix
Qwen · DavidAU
Params8.95B
Context256K
Best fitBF16 19.5 GB
QW
Qwen2.5 Coder 14B Instruct
Qwen · unsloth
Params14.8B
Context128K
Best fitF16 31.7 GB
DE
DeepSeek V3.1
DeepSeek · bartowski
Params670B
Context160K
Q4_K_M409.2 GB
MI
cognitivecomputations_dolphin-2.6-mistral-7b
Mistral · TheBloke
Params7.24B
Context32K
Best fitQ8_0 9.3 GB
LF
lfm2.5 2.6b fable5 coding agent heretic
Lfm · saidutta69
Params2.7B
Context128K
Best fitF16 7.9 GB