hugging-quants
Browse models
Open models you can download and run. Pick your memory to see what fits.
Model results
Showing 12 of 180,842 models
Fit is a memory estimate, not a speed test.
LM
lmstudio-community
Hermes-4-70B-MLX-4bit
Chat & write39.69 GBLlama 3 Community (from base model)↓ 60.4K60,361 catalog downloads
LM
lmstudio-community
Hermes-4-70B-MLX-6bit
Chat & write57.33 GBLlama 3 Community (from base model)↓ 56.3K56,309 catalog downloads
LM
lmstudio-community
DeepSeek-R1-Distill-Qwen-14B-GGUF
Chat & write8.99 GBMIT (from base model)↓ 35.8K35,779 catalog downloads
LM
lmstudio-community
Qwen3-4B-GGUF
Chat & write2.5 GBApache 2.0 (from base model)↓ 17.2K17,210 catalog downloads
LM
lmstudio-community
DeepSeek-R1-Distill-Qwen-7B-GGUF
Chat & write4.68 GBMIT (from base model)↓ 16.6K16,641 catalog downloads
HU
hugging-quants
Llama-3.2-1B-Instruct-Q8_0-GGUF
Chat & write1.32 GBLlama 3.2 Community (from base model)↓ 8.7K8,724 catalog downloads
BA
bartowski
openai_gpt-oss-120B-GGUF
Chat & writeApache 2.0 (from base model)↓ 8.5K8,548 catalog downloads
LM
lmstudio-community
DeepSeek-R1-Distill-Llama-8B-GGUF
Chat & write4.92 GBMIT (from base model)↓ 5.8K5,782 catalog downloads
LM
lmstudio-community
ERNIE-4.5-21B-A3B-PT-GGUF
Chat & write13.5 GBApache 2.0 (from base model)↓ 4.3K4,252 catalog downloads
NA
NANI-Nithin
MiniCPM5-1B-GGUF
Chat & write688 MBApache 2.0 (from base model)↓ 3.9K3,892 catalog downloads
BA
Chat & write1.93 GBApache 2.0 (from base model)↓ 3.1K3,150 catalog downloads