Skip to content
Other

HDM-Qwen3.8-27B

smart reasoning router for Qwen

2 min readupdated

A compact routing module (1.31M parameters, weighing just 5.3 MB) accompanying the paper "The Value of Thinking: Learning When to Reason in Hybrid Decision Models." It attaches to a frozen Qwen/Qwen3.8-27B base model to stop it from wasting extra tokens on long chains of thought when a direct answer works just fine. First, the main model runs a single quick pass without generating text, while the router evaluates the hidden state and eight response statistics to predict whether reasoning will actually improve the final output. Built for developers and researchers deploying large LLMs who want fine-grained control over the trade-off between accuracy and compute.

Key features

  • Evaluates four possible outcomes: whether reasoning will fix an error from a quick answer or just make things worse.
  • Controlled via a cost threshold λ, which can be set per request without retraining the router.
  • Virtually zero memory overhead — the weights file takes up only 5.3 MB, and the base Qwen3.8-27B model remains untouched.
  • Runs on the SGLang 0.5.9 backend (transformers is also supported, though feature differences can alter routing behavior).

What you can do

  • Hook it up to a Qwen3.8-27B inference server via the hde-serve utility to cut down on reasoning tokens for straightforward multiple-choice questions.
  • Set up dynamic request routing in your API by passing the lambda parameter inside the routing field to tune thinking depth per task.
  • Retrain the router for your own base model, a different layer, or another compute precision — according to the authors, fitting takes just a few minutes.

Example

from huggingface_hub import hf_hub_download
from hde.core.block import DecisionHead

path = hf_hub_download("fredreick/HDM-Qwen3.8-27B", "head-27b-mmlu-pro.safetensors")
block = DecisionHead.load(path)
Read moreDetails
MMLU-Pro benchmark (346 held-out questions across chemistry, economics, and psychology): at λ = 0.05, accuracy hits 89.0% (compared to 90.2% with reasoning always on and 65.0% with it off), using 78% of the reasoning tokens.
JevBench benchmark (231 questions, zero fine-tuning on this dataset): at λ = 0, accuracy reaches 98.7% versus 99.1% in always-think mode, using 82% of the tokens.
Training: 1,154 multiple-choice questions from MMLU-Pro with a 4,096-token reasoning budget.
Limitations: tied to a specific Qwen/Qwen3.8-27B revision, layer -1, and coded readout; non-multiple-choice question formats haven't been tested, and the router still frequently sends hopeless questions into reasoning.
Discuss Telegram 0

Will it run?

Runs in BF16

Fits without quantisation.

  • BF16weights 0.0 GB · ready files0.5 GB
  • FP8 / INT8recommendedweights 0.0 GB0.5 GB
  • 4-bitweights 0.0 GB0.5 GB

Tip: go 8-bit.FP8 / INT8 is within about a percent of full precision in quality, takes half the memory and runs faster on RTX 40/50 and H100. Full precision only pays off for fine-tuning.

What to get for this model

Massed ComputeOpen Massed Compute

Your own GPU: FP8 / INT8 — from RTX 2060 · BF16 — from RTX 2060

Massed Compute hourly prices, November 2026. The discounted price applies with the coupon at checkout.

Estimate: weights plus working memory. Long videos, high resolutions and long contexts need more.

Run it on Massed Compute

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    # fredreick/HDM-Qwen3.8-27B
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download fredreick/HDM-Qwen3.8-27B --local-dir ~/models/HDM-Qwen3.8-27B
    # The model is in ~/models. How to run it is in the model card (link above).
    Add more LoRAs to HDM-Qwen3.8-27B
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (2)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

Model family

New posts about versions of Qwen3.8-27B (quants, finetunes, LoRAs) will show up under the bell.

Quantised versions 12All on Hugging Face
Fine-tunes 12All on Hugging Face
LoRAs and adapters 2All on Hugging Face

About the model

fredreick/HDM-Qwen3.8-27B
Author
fredreick
Category
Other
Released
Posted

On NeyroLearn

Hugging Face

00

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments