GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
PrimeIntellect
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
PrimeIntellect
Model Tree
Qwen/Qwen3.5-0.8B
Input Modalities
Output Modalities
Supported Functionality
21814b401 (branch ci/qwen3_5-ci, contains the Qwen3.5 tied lm_head fix #3863 and the CP fix #3864).uv run sft @ sft.toml), 1 H200:toml
max_steps = 10 [model]name = "Qwen/Qwen3.5-0.8B" [data]name = "PrimeIntellect/Reverse-Text-SFT"seq_len = 4096batch_size = 32 [optim]lr = 2e-5<think>\n\n</think>\n\n prefix, the same as RL generation.Qwen3_5ForConditionalGeneration like the base model.reverse-text eval reward (LCS ratio, 256 prompts, temperature 1, 128 max tokens): 0.31 (base model: 0.03 on 32 prompts).max_steps = 10 [model]name = "Qwen/Qwen3.5-0.8B" [data]name = "PrimeIntellect/Reverse-Text-SFT"seq_len = 4096batch_size = 32 [optim]lr = 2e-5