This guide demonstrates how to run a highly compressed 2-bit version of Qwen3.8-27B that maintains tool-calling capabilities and outperforms the full model on specific benchmarks.
AI-generated summary. Check the original reporting for context and accuracy.
Source excerpt
This is the available feed excerpt, which may be shortened or in the publisher’s original language.
In this tutorial, we work with Underdog Saluki 27B, a 7.9 GB build of Qwen3.8-27B that its makers say keeps tool calling intact at about two bits per weight and even edges out the full 54 GB model on their own 120-task benchmark. Saluki is built on ISTA-DASLab’s GSQ-RCO quantization of the same model, so we put both files side by side in stock llama.cpp. We start with the files themselves: a tensor-by-tensor diff of the two GGUF headers, then a byte-level comparison that shows whether Saluki is a remix of ISTA’s bits or a changed model. We then serve each file on one GPU, read its memory and speed, and score both on the same seeded 120 tasks from the Berkeley Function Calling Leaderboard, using BFCL’s own checker with strict and lenient parsing. Copy CodeCopiedUse a different Browserimport os import re import ast import sys import json import math import copy import enum import glob import time import types import random import shutil import struct import hashlib import tarfile import platform import traceback import subprocess import collections import urllib.request import urllib.error RESULTS = {} # step -> one-line result, for the summary table CLAIMS = [] # (step, claim, held) rows; held is True, False or None (not decided in this run) CURRENT = ["1"] def banner(title): print("\n" + "=" * 78) print(title) print("=" * 78) def section(name): def wrap(fn): def run(*a, **kw): CURRENT[0] = name.split(".")[0] banner(name) t0 = time.time() try: out = fn(*a, **kw) RESULTS[name] = out if isinstance(out, str) else "ok" return out except Exception as e: RESULTS[name] = f"SKIPPED / FAILED -> {type(e).__name__}: {e}" print(f"\n[!] {name} did not complete: {type(e).__name__}: {e}") traceback.print_exc(limit=3) return None finally:
About priority
An automated sorting aid based on source trust, keywords, and entities, on a scale of 1–12. High: 9–12; medium: 6–8; low: 1–5. It does not measure urgency, verify reporting, or indicate editorial endorsement.
Nanbeige4.3-33B is a significant open-source release because it offers a high-performing, Apache 2.0-licensed 33B model specifically optimized for agentic coding and long-context tasks.
Carbon-X democratizes genomic analysis by offering a free, open-source model that translates raw DNA into plain English, enabling labs to process sensitive data privately.
TokenGate accelerates long-context LLM processing by up to 11.3x without accuracy loss, significantly reducing latency and memory usage for large-scale applications.