GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
willamazon1
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
willamazon1
Model Tree
Qwen/Qwen3.6-35B-A3B
Input Modalities
Output Modalities
Supported Functionality
python
import torchfrom transformers import AutoModelForCausalLM, AutoProcessorrepo = "willamazon1/qwen3.6-35b-a3b-miles-multievo-v2-iter024"proc = AutoProcessor.from_pretrained(repo)model = AutoModelForCausalLM.from_pretrained(repo, dtype=torch.bfloat16, device_map="auto")
Converted from a Megatron-LM torch_dist training checkpoint to HuggingFace
safetensors with slime's
tools/convert_torch_dist_to_hf.py, using --vocab-size 248320 to strip
embedding padding and -a/--add-missing-from-origin-hf so the vision tower —
which the language-model-only torch_dist checkpoint does not carry — is taken
from the base model. MoE experts are stored in the grouped/fused layout
(mlp.experts.gate_up_proj / down_proj).
Every shard was checked for NaN/Inf and the full tensor key set was diffed against a known-good conversion of this architecture before upload.