GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
khazarai
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
khazarai
Model Tree
khazarai/Qwen3-4B-Qwen3.6-plus-Reasoning-Distilled
khazarai/Qwen3-4B-Kimi2.5-Reasoning-Distilled
Input Modalities
Output Modalities
Supported Functionality
| Model | Score |
|---|---|
| khazarai/Qwen3-4B-Qwen3.6-plus-Reasoning-Slerp | 77.18 |
| khazarai/Qwen3-4B-Kimi2.5-Reasoning-Distilled | 76.09 |
| khazarai/Qwen3-4B-Qwen3.6-plus-Reasoning-Distilled | 75.64 |
| Qwen/Qwen3-4B-Thinking-2507 | 73.73 |
The following models were included in the merge:
The following YAML configuration was used to produce this model:
yaml
models: - model: khazarai/Qwen3-4B-Kimi2.5-Reasoning-Distilled - model: khazarai/Qwen3-4B-Qwen3.6-plus-Reasoning-Distilledmerge_method: slerpbase_model: khazarai/Qwen3-4B-Kimi2.5-Reasoning-Distilledparameters: t: - filter: embed_tokens value: 1 - filter: lm_head value: 1 - value: 1 - filter: self value: [0, 0.1, 0.2, 0.3, 0.5, 0.7, 0.8, 0.9, 1] dtype: bfloat16models: - model: khazarai/Qwen3-4B-Kimi2.5-Reasoning-Distilled - model: khazarai/Qwen3-4B-Qwen3.6-plus-Reasoning-Distilledmerge_method: slerpbase_model: khazarai/Qwen3-4B-Kimi2.5-Reasoning-Distilledparameters: t: - filter: embed_tokens value: 1 - filter: lm_head value: 1 - value: 1 - filter: self value: [0, 0.1, 0.2, 0.3, 0.5, 0.7, 0.8, 0.9, 1] dtype: bfloat16