Skip to content
Other

strands-decider-2B

Q8_0 GGUF с головой-решателем

1 min readupdated

Это Q8_0 GGUF-версия strands-decider-2B-qwen3.5-v1-2610 от команды Strands Agents, собранная на базе Qwen3.5-2B-Base с объединённым LoRA-решателем. Это не чат-модель: llama-server отдаёт эмбеддинги, а decide.py превращает скрытые состояния в ответы через отдельный pointer head. Репозиторий — зеркало с файлами, нужными для запуска.

Ключевые особенности

  • База Qwen3.5-2B-Base, LoRA decider объединён в GGUF, pooling_type = last.
  • llama-server запускает модель в режиме --embeddings; контекст 8192.
  • В комплекте head.safetensors и клиент decide.py на numpy.
  • Есть запись для каталога Lemonade: recipe llamacpp, labels embeddings.
  • Лицензия Apache-2.0, как у decider и Qwen3.5-2B-Base.

Пример

llama-server -m strands-decider-2B-qwen3.5-v1-2610-Q8_0.gguf --embeddings -c 8192 -b 4096 -ub 4096 --port 8080
pip install numpy safetensors
python decide.py
ПодробнееQ8_0 GGUF; база Qwen3.5-2B-Base; LoRA merged; pooling_type = last.
Не чат-модель: нужны llama-server с --embeddings, head.safetensors и decide.py.
Контекст 8192, batch/ubatch 4096; лицензия Apache-2.0.
Бенчмарки и требования к VRAM в карточке не указаны.
Discuss Telegram 0 79

Will it run?

Runs in GGUF Q8_0

The most precise of the ready quantised files fits.

  • GGUF Q8_0recommendedweights 1.9 GB · ready files2.6 GB

Tip: go 8-bit.GGUF Q8_0 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: GGUF Q8_0 — 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.

    # denkbox/strands-decider-2B-qwen3.5-v1-2610-Q8_0-GGUF
    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 denkbox/strands-decider-2B-qwen3.5-v1-2610-Q8_0-GGUF --local-dir ~/models/strands-decider-2B-qwen3.5-v1-2610-Q8_0-GGUF
    # The model is in ~/models. How to run it is in the model card (link above).
  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 strands-decider-2B-qwen3.5-v1-2610-Q8_0-GGUF (quants, finetunes, LoRAs) will show up under the bell.

No known relatives of this model yet. All derivatives on Hugging Face

About the model

denkbox/strands-decider-2B-qwen3.5-v1-2610-Q8_0-GGUF
Author
denkbox
Category
Other
Released
Posted

On NeyroLearn

Hugging Face

790

Ask AI about this model

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

Comments