GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
zrlu
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
zrlu
Model Tree
OBLITERATUS/Qwen3.8-27B-OBLITERATED
Input Modalities
Output Modalities
Supported Functionality
Apache-2.0 — inherited unchanged from the base model (Qwen3.8-27B lineage). Weight-only quantization; no rights are widened.
gptqmodel==7.3.2 on CUDA (RTX 5090), lazy checkpoint loading;
calibration wikitext-2 (or bundled fallback text).markdown
bits=4, group_size=128, desc_act=false, sym=true, lm_head=false, dynamic={"-:.*mtp.*":{}}
Qwen3_5ForConditionalGeneration, image_token_id 248056.Served with the B70 one-click image (zrlu/qwen38-27b-arc-pro-b70:2026.08.24,
vLLM XPU 0.27.2rc1.dev77 + kernels 0.1.12.3, MTP4 + draft-INT4 S+M1 overlay,
prefix caching, qwen3_xml tool parser, fp8 KV):
bash
docker run -d --name qwen38-<tag> --init --device /dev/dxg --ipc=host --shm-size=16g \--restart unless-stopped --security-opt seccomp=unconfined --cap-add SYS_NICE \-p 127.0.0.1:8000:8000 \-v /usr/lib/wsl/lib:/usr/lib/wsl/lib:ro -v /usr/lib/wsl/drivers:/usr/lib/wsl/drivers:ro \-e HF_REPO="zrlu/OBLITERATUS-Qwen3.8-27B-OBLITERATED-GPTQ-Int4-sym-G128-MTP-BF16-B70" \zrlu/qwen38-27b-arc-pro-b70:2026.08.24
First start auto-downloads this repo into /model (~18 GB). Full setup,
pi-agent wiring and benchmark methodology live in the
GitHub repository
(benchmarks included).
python
from transformers import AutoModelForCausalLM, AutoTokenizertok = AutoTokenizer.from_pretrained("zrlu/OBLITERATUS-Qwen3.8-27B-OBLITERATED-GPTQ-Int4-sym-G128-MTP-BF16-B70")m = AutoModelForCausalLM.from_pretrained("zrlu/OBLITERATUS-Qwen3.8-27B-OBLITERATED-GPTQ-Int4-sym-G128-MTP-BF16-B70",device_map="auto")
Signed: zrlu. Quantization GPU: RTX 5090; GPU of use: Intel Arc Pro B70.