GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
airun-ai
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
airun-ai
Model Tree
XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B
Input Modalities
Output Modalities
Supported Functionality
nDCG@10, BM25 top-20, packed_all, one pass:
| Adapter | SciFact | NFCorpus |
|---|---|---|
| BM25 | 0.662 | 0.306 |
| bge-reranker-v2-m3 | 0.721 | 0.326 |
| Control: LoRA on all tokens, same 150 steps | 0.744 | 0.351 |
| Activated (this adapter) | 0.740 | 0.351 |
Cache reuse on 100 HotpotQA distractor questions (10 paragraphs, median state 1.4k tokens, H100): state pass 64 ms, 10 probes 85 ms (recall@3 0.97). Answering by continuing the reranking cache: EM 0.61 / F1 0.750, answer latency 138 ms; re-prefilling the top-3 passages instead: EM 0.59 / F1 0.754, 181 ms.
Correctness check (Qwen3.5-0.8B, randomised LoRA): with the patch, the adapter-on state cache equals the base model's bitwise across all 48 cache tensors (attention KV, DeltaNet conv and recurrent states).
code/alora_patch.py: the activated-adapter patch for the Kev runtime (training and inference).code/train_alora.py: training entry (wraps kev.train, requires --shared_prefix 1).code/check_alora.py: bitwise cache-identity check.code/chat_alora.py: chat-identity check vs the base.code/e1_rerank_alora.py: BEIR reranking evaluation (--alora 1).code/e5_cache_reuse.py: HotpotQA rerank-then-continue-the-cache evaluation.Runtime: Kev at commit 0a6d3faf; see requirements.txt.
bibtex
@misc{metinov2026glance, title = {Glance: The Generator Is Its Own Reranker}, author = {Metinov, Adilet and Arziev, Chingiz}, year = {2026}, publisher = {Airun Intelligence Labs}, note = {arXiv preprint, identifier to be added}}License: Apache-2.0. See LICENSE and NOTICE; redistributions must retain the NOTICE attribution.
@misc{metinov2026glance, title = {Glance: The Generator Is Its Own Reranker}, author = {Metinov, Adilet and Arziev, Chingiz}, year = {2026}, publisher = {Airun Intelligence Labs}, note = {arXiv preprint, identifier to be added}}