Skip to content
Other

mradermacher/vox-mens-qwen3.5-9b-GGUF

quantized language model builds

2 min read

This release provides static quantizations in GGUF (a format for running large language models on consumer hardware) for the brbrainerd/vox-mens-qwen3.5-9b model. It is designed for running text tasks on standard desktops and laptops with varying amounts of VRAM and system RAM. With a wide selection of compression levels, you can pick the file that best fits your hardware while balancing inference speed and output quality. Useful for developers and enthusiasts testing local LLMs (large language models).

Key features

  • Broad selection of quantization formats, ranging from lightweight Q2_K to high-precision Q8_0 and f16.
  • Includes popular, well-balanced options like Q4_K_M and Q4_K_S for fast inference.
  • Uses the GGUF format for broad compatibility with mainstream local clients and frameworks.
  • Optimized to run on consumer hardware without requiring high-end server GPUs.

What you can do

  • Run the model locally on your machine using any GGUF-compatible software.
  • Integrate the model into local chatbots and development environments for text tasks.
  • Benchmark different quantization levels (such as IQ4_XS or Q5_K_M) to compare quality loss against the original weights.

Example

To run the model, download your preferred quantization file (such as Q4_K_M) from the repository and load it into a supported app or library like llama.cpp by pointing your configuration to the file path.

Read moreDetails
Base model: brbrainerd/vox-mens-qwen3.5-9b
Available file sizes: from 3.9 GB (Q2_K) to 18.0 GB (f16)
Recommended variants: Q4_K_S, Q4_K_M (fast) and Q8_0 (best quality)
Weighted and imatrix quantizations are not included in this release
Discuss Telegram 0

Will it run?

Runs in GGUF F16

The most precise of the ready quantised files fits.

  • GGUF F16weights 17 GB · ready files19 GB
  • GGUF Q8_0recommendedweights 8.9 GB · ready files10 GB
  • GGUF Q6_Kweights 6.9 GB · ready files8.0 GB
  • GGUF Q5_K_Mweights 6.0 GB · ready files7.1 GB
  • GGUF Q5_K_Sweights 5.9 GB · ready files7.0 GB
  • GGUF Q4_K_Mweights 5.2 GB · ready files6.3 GB
  • GGUF Q4_K_Sweights 5.0 GB · ready files6.0 GB
  • GGUF IQ4_XSweights 4.9 GB · ready files5.9 GB
  • GGUF Q3_K_Lweights 4.6 GB · ready files5.5 GB
  • GGUF Q3_K_Mweights 4.3 GB · ready files5.2 GB
  • GGUF Q3_K_Sweights 4.0 GB · ready files4.9 GB
  • GGUF Q2_Kweights 3.6 GB · ready files4.4 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 2080 Ti · GGUF F16 — from RTX 4090

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.

    # mradermacher/vox-mens-qwen3.5-9b-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 mradermacher/vox-mens-qwen3.5-9b-GGUF --local-dir ~/models/vox-mens-qwen3.5-9b-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

  1. Qwen3.5-9B-Basefamily root
  2. Qwen3.5-9B
  3. vox-mens-qwen3.5-9b
  4. vox-mens-qwen3.5-9b-GGUF

New posts about versions of Qwen3.5-9B-Base (quants, finetunes, LoRAs) will show up under the bell.

Quantised versions 12All on Hugging Face
Fine-tunes 12All on Hugging Face
LoRAs and adapters 6All on Hugging Face
Merges 1All on Hugging Face

About the model

mradermacher/vox-mens-qwen3.5-9b-GGUF
Author
mradermacher
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

Computer vision

Script2Play-4B

Script2Play-4B