GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
schneewolflabs
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
schneewolflabs
Model Tree
hemlang/Hemlock-Qwen3.8-27B
Input Modalities
Output Modalities
Supported Functionality
| axis | Hemlock-3.8 | B0-27B |
|---|---|---|
| egirl 47-case operator bench | 47/47 | 42/47 |
| kirabench (end-to-end task completion via egirl + Codex) | 6/6 | 6/6, faster |
| censorship (strict, single-sample) | 27/29 | 28/29 |
| safety asymmetry (refuses actual harm) | 2/2 | 2/2 |
| prose distance vs contemporary fiction | 0.528 | 0.525 |
| stance rate (has opinions) | 16.7% | 8.3% |
| hembench | 79.9% | 73.4% |
| ARC / wiki-clean ppl | 65.9 / 10.01 | 66.2 / 9.93 |
| identity | "Qwen" | Schneewolf Labs |
The egirl-bench dip is five known single-tool-call reflexes (three delegation prompts
answered with git_status, two trivial edits answered with a file search). They do not
reach task completion: on kirabench — six sandboxed engineering tasks driven through the
real egirl harness with Codex as the code agent, judged only by deterministic checkers —
B0-27B goes 6/6 and fixed a failing-test task ~9× faster than its base.
mtp.* tensors are untouched from the base; mmproj included
in the GGUF repo. --spec-type draft-mtp works.bash
llama-server -m B0-27B-Q8_0.gguf -ngl 99 -c 16384 --jinja -fa on -np 1 \--spec-type draft-mtp --spec-draft-n-max 4