Use unsloth FP16 GGUF to quantize IQ1_M. AMD Ryzen 7 Pro 8845HS + 128 GB DDR5 5600 RAM in LM Studio with complete GPU offloading yields around 5 token/s.
- Downloads last month
- 160
Hardware compatibility
Log In
to view the estimation
1-bit
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for lovedheart/Qwen3-253B-A22B-IQ1_M
Base model
Qwen/Qwen3-235B-A22B