This is an archived repository that redirects users to the canonical recipe for the GLM-5.2 Quantrio INT4/INT8 mixed abliterated model with DFlash speculative decoding.
12
No data
1
1
NOASSERTION
2026-07-18
It provides a clear, authoritative pointer to the only supported stack for a specific high-performance LLM configuration, preventing installation of an outdated version.
Canonical (only) recipe:
| Weights | https://huggingface.co/drowzeys/keys-latest-GLM-5.2-Quantrio-INT4-INT8mixed-Abliterated |
| DFlash draft | https://huggingface.co/drowzeys/keys-latest-GLM-5.2-DFlash-FP8 |
| Profile | DFlash k=12 · 128k · seqs=4 · UTIL 0.85 · KV pin 10 GiB |
This older C1-30toks title is archived to prevent agents/humans from installing the wrong stack.
GLM-5.2 Quantrio INT4/INT8 Mixed Abliterated — SPEED=1 C1≈30 tok/s @ 128k on 4x DGX Spark. Step-by-step recipe, image bake, results.
Similar projects matched by category, topics, and programming language.
Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.
A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.
mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.