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.
MI
MiniCPM V 4.7 35B A3B
MiniCPM · openbmb
Params34.7B
Context256K
Best fitQ6_K 29.7 GB
LL
Llm Jp 4 33b Thinking
Llm · llm-jp
Params33.2B
Context64K
Best fitQ4_K_M 22.8 GB
GR
Granite 4.2 3b
Granite · ibm-granite
Params3.66B
Context128K
Best fitBF16 8.5 GB
GR
Granite 4.2 8b
Granite · ibm-granite
Params8.79B
Context128K
Best fitBF16 19.4 GB
GR
grug 27b
Grug · ProCreations
Params27B
Context256K
Best fitQ8_0 31.2 GB
LF
LFM2.5 Audio 1.5B
Lfm · LiquidAI
Params190M
Context125K
Best fitF16 3.0 GB
QW
Qwen3.5-0.8B
Qwen · unsloth
Params752M
Context256K
Best fitBF16 2.4 GB
QW
Qwen-Agentworld-35B-A3B
Qwen · unsloth
Params34.7B
Context256K
Best fitQ6_K 30.5 GB
QW
Ternary-Bonsai-2-2B
Qwen · prism-ml
Params1.88B
Context256K
Smallest0.4 GB
GP
gpt-oss-20b
gpt-oss · ggml-org
Params870M
Context128K
Best fitMXFP4 12.6 GB
GE
Gemma 3 1b It
Gemma · ggml-org
Params1B
Context32K
Best fitF16 2.7 GB
QW
Qwythos-27B
Qwythos · empero-ai
Params27B
Context1024K
Best fitQ8_0 31.7 GB
MI
MiniMax H3
Minimax · leejet
Params20.1B
Context—
Best fitQ4_K_M 21.5 GB
QW
Qwopus3.6 27B Fusion
Qwen · KyleHessling1
Params27.3B
Context256K
Best fitQ8_0 31.7 GB
GE
Google_Gemma 4 12B It Qat Q4_0 Unquantized
Gemma · lmstudio-community
Params11.9B
Context256K
Best fitQ4_0 20.4 GB
SA
Sage A1.5 Q4 K M
Sage · InternScience
Params35.5B
Context256K
Best fitQ4_K_M 22.9 GB
GE
gemma 4 12B agentic fable5 composer2.5 v2 3.5x tau2
Gemma · yuxinlu1
Params11.9B
Context256K
Best fitQ8_0 26.1 GB
SM
TwIL LM3
SmolLM · webAI-Official
Params3.08B
Context64K
Best fitF16 7.3 GB
QW
Qwen2.5-Vl-7B-Instruct
Qwen · unsloth
Params7.62B
Context125K
Best fitBF16 16.2 GB
GP
gpt-oss-120b
gpt-oss · ggml-org
Params800M
Context128K
Best fitBF16 2.1 GB
LI
Ling 3.0 Tiny
Ling · bloomer010
Params7.89B
Context128K
Best fitBF16 20.7 GB
GL
Glm-4.7-Flash
GLM · unsloth
Params30B
Context198K
Best fitQ6_K_XL 27.5 GB
HE
Hemmingway 1
Hemmingway · mradermacher
Params27.3B
Context256K
Best fitQ8_0 31.7 GB
GE
POCKET 26B
Gemma · FINAL-Bench
Params25.2B
Context256K
Best fitQ4_K_M 25.3 GB
GR
Granite 4.2 30b
Granite · ibm-granite
Params29.3B
Context128K
Best fitQ6_K 26.7 GB
BO
Bonsai-27B
Bonsai · lmstudio-community
Params27B
Context256K
Best fitQ1_0 6.5 GB
QW
qwen2.5-3b-instruct
Qwen · Qwen
Params3.4B
Context32K
Q4_K_M2.1 GB
SP
spark s1 4b v6
Spark · abhishek085
Params4.21B
Context256K
Best fitBF16 10.0 GB
QW
Qwen2.5 Coder 1.5B Instruct GGUF
Qwen · Qwen
Params1.78B
Context32K
Best fitQ8_0 2.6 GB
QW
Qwen2.5 7B Instruct
Qwen · bartowski
Params7.62B
Context32K
Best fitF16 16.2 GB