Qwen3.6-35B-A3B-MTP-L4 kyr0 · COMPLETED
Deploy Qwen3.6-35B-A3B (Q4_K_XL) + MTP speculative decoding on a single NVIDIA L4 24GB — GCP g2-standard-8 — via the official llama.cpp Docker image. Decode-optimized to ~92–100 tok/s, lossless (full GPU residency + ECC-off).
github.com/kyr0/Qwen3.6-35B-A3B-MTP-L4 · ★ 0 · Forks 0 · Size 529 KB
SUMMARY
Technologies 4
Scored 4
Observed 4
Practices 6
Evidence 4
Skips 0
COVERAGE
Analyzed 9 files · 26 commits · 0 API calls
TECHNOLOGIES & DEPTH
Dockerfile LANGUAGE Depth 70
1 files · PRODUCTION
Shell LANGUAGE Depth 70
4 files · PRODUCTION
Markdown LANGUAGE Depth 70
1 files · PRODUCTION
YAML LANGUAGE Depth 70
2 files · PRODUCTION
PRACTICES
documentation · observedautomated_tests · absentcontinuous_integration · observedcontainerization · observedlinting · absentformatting · absent
ACTIVITY & OWNERSHIP
First commit 2026-05-23
Last commit 2026-06-27
Active months 2
Commits 26