GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
inference-optimization
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
inference-optimization
Model Tree
thinkingmachines/Inkling
Input Modalities
Output Modalities
Supported Functionality
The following parameters were reduced from the original model:
| Parameter | Original | Tiny |
|---|---|---|
text_config.num_hidden_layers | 66 | 12 |
text_config.hidden_size | 6144 | 1024 |
text_config.intermediate_size | 24576 | 4096 |
text_config.num_attention_heads | 64 | 8 |
text_config.num_key_value_heads | 8 | 2 |
text_config.swa_num_attention_heads | 64 | 8 |
text_config.swa_num_key_value_heads | 16 | 4 |
text_config.n_routed_experts | 256 | 8 |
text_config.num_experts_per_tok | 6 | 4 |
text_config.moe_intermediate_size | 3072 | 512 |
text_config.num_mtp_layers | 8 | 1 |
vision_config.n_layers | 4 | 1 |
vision_config.hidden_size | 1024 | 256 |
vision_config.decoder_dmodel | 6144 | 1024 |
audio_config.decoder_dmodel | 6144 | 1024 |
Layer type patterns are preserved: 2 repetitions of [5× hybrid_sliding + 1× hybrid], with the first 2 MLP layers as dense and the rest as sparse (MoE).
Single safetensors file (model.safetensors). Key naming matches the original checkpoint format (model.llm.*, model.audio.*, model.visual.*).
python
from transformers.models.inkling import InklingForConditionalGenerationfrom transformers import AutoTokenizermodel = InklingForConditionalGeneration.from_pretrained("inference-optimization/Inkling-0.6B-A0.6B", device_map="auto")tokenizer = AutoTokenizer.from_pretrained("inference-optimization/Inkling-0.6B-A0.6B")input_ids = tokenizer("According to all known laws", return_tensors="pt").input_ids.to(model.device)output = model.generate(input_ids, max_new_tokens=20)print(tokenizer.decode(output[0]))
This model was created using the llm-compressor create-tiny-model claude skill.
inspect_config.pysave_tiny_model.py — all-zero params fixed post init_weightsvalidate_tiny_model.pyembed_tokens weights require explicit re-initialization after init_weights() (they initialize to zero in this architecture). The save script applies a fixup: any all-zero, non-finite, or extreme-valued parameter is re-initialized with kaiming_uniform / normal / ones as appropriate.model.mtp.*) are not included, as InklingForConditionalGeneration does not expose them through its standard interface.Success: 1.4451 <= 10.0