The image-editing prompt rewriter for Qwen-Image-2.1, a fine-tuned Qwen3.5-VL 9B that turns a short edit instruction plus 1–N input images into a detailed English edit prompt, with its refusal behaviour removed by Heretic directional ablation. bf16, same shapes and parameter count as the source; nothing else was changed. systemprompt.txt is included and required. It defines the output format. It is the unmodified file from the source repo. The second row is an independent evaluation of the exported weights with Heretic's evaluatemodel. Refusals were measured on mlabonne/harmfulbehaviors and KL divergence (damage to ordinary behaviour, first-token distributions) on mlabonne/harmlessalpaca…
Open-weight model · Image and text to text
LucidVitality-9b
by Matthew Andrews BlueNipples/LucidVitality-9b
LucidVitality-9b is an open-weight model for image and text to text from Matthew Andrews. It has 9.4B parameters and a 262,144-token context. At 16-bit it needs about 22.6 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index. It draws 52 downloads a month.
LucidVitality-9B is a little goer. It's a roleplay or creative focused merge of two Qwen3.5 9b variants for people with absolute potatoes, like myself.
Parameters9.4B
Context262,144
Weights18.8 GB
License—
AccessOpen weights
Monthly Downloads52
Runs On
What it takes to serve LucidVitality-9b (9.4B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 18.8 GB | 22.6 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 9.4 GB | 11.3 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 4.7 GB | 5.6 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 24, 2026.
LucidVitality-9b on every accelerator the SAVRN Index prices, at every precision
Model Card
LucidVitality-9B is a little goer. It's a roleplay or creative focused merge of two Qwen3.5 9b variants for people with absolute potatoes, like myself. It marries the improved prose of Darkhn's Qwen3.5-9B-Animus-V13.0 with the lower looping, higher EOS exit, and slightly more coherency (compared to base) from Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED of DavidAU's making. I haven't merged anything for a long time, as it's been a hard time for finetuning. They rarely increase prose quality, often deeply lose intelligence over base (even when tuned for intelligence or agentic). Base model's getting tough to beat. So it was a pleasant surprise to find two models that each…
Excerpt from the card by Matthew Andrews.
Configuration
- Architecture
- Qwen3_5ForConditionalGeneration
- Context length (tokens)
- 262,144
- Layers
- 32
- Hidden size
- 4,096
- Feed-forward size
- 12,288
- Attention heads
- 16
- Key/value heads
- 4
- Head dimension
- 256
- Vocabulary size
- 248,320
- Model type
- qwen3_5
Identity and Version
- Repository
- BlueNipples/LucidVitality-9b
- Publisher
- Matthew Andrews
- Task
- Image and text to text
- Modality
- Image and text
- Library
- transformers
- Parameters
- 9.4B parameters
- Languages
- Not stated by the source
- Revision
- ef0b392700df7f49f3fdf1de99780a46e15c08f0
- First published
- 2026-09-14
- Last updated
- 2026-09-22
Files and Weights
11 files, 18.8 GB in total. The weights are 4 files totalling 18.8 GB in safetensors.
Weights4 files · 18.8 GB
Configuration3 files · 72.5 KB
Tokenizer2 files · 20.0 MB
Documentation1 file · 3.4 KB
Repository1 file · 1.6 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model-00001-of-00004.safetensors | Weights | 4.9 GB | 34256e9a2070 |
| model-00002-of-00004.safetensors | Weights | 5.0 GB | 9fa4607b4d81 |
| model-00003-of-00004.safetensors | Weights | 5.0 GB | b3655ba0f91c |
| model-00004-of-00004.safetensors | Weights | 3.9 GB | 58fd0a6a65da |
| config.json | Configuration | 2.9 KB | — |
| mergekit_config.yml | Configuration | 422 B | — |
| model.safetensors.index.json | Configuration | 69.2 KB | — |
| README.md | Documentation | 3.4 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 20.0 MB | 87a7830d63fc |
| tokenizer_config.json | Tokenizer | 1.1 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 18.8 GB
Download from Matthew Andrews
Released by Matthew Andrews through its official repository on Hugging Face.
Built From
- Derived from Darkhn/Qwen3.5-9B-Animus-V13.0
- Derived from DavidAU/Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED
- Merged from Darkhn/Qwen3.5-9B-Animus-V13.0
- Merged from DavidAU/Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 18.8 GB |
| 16-bit | 18.8 GB |
| 8-bit | 9.4 GB |
| 4-bit | 4.7 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About LucidVitality-9b
How much GPU memory does LucidVitality-9b need?
About 22.6 GB at 16-bit and 5.6 GB at 4-bit: the weights (9.4B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run LucidVitality-9b on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
What is LucidVitality-9b's context length?
262,144 tokens, from the maximum position embeddings in its published configuration.
Similar Models
NVFP4 (4-bit floating point, W4A4) build of darrellbest/Qwen-Image-2.1-PE-I2I-Heretic, the refusal-ablated image-editing prompt rewriter for Qwen-Image-2.1. For vLLM on NVIDIA Blackwell GPUs, which run NVFP4 natively. 11 GB instead of 18 GB. systemprompt.txt is included and required, exactly as for the original. The linear-attention layers carry a recurrent state and the vision tower encodes the input image; both were left in bf16, as other quantizations of this model family do. That is why the file is 11 GB rather than ~6 GB. Made with llm-compressor 0.13.0 (QuantizationModifier, scheme="NVFP4"), calibrated on 64 samples in the model's real input format: its own system prompt, an edit…
This model is a fine-tuned version of Qwen/Qwen3.5-9B-Base on the Omni-Edu-70K dataset. The following hyperparameters were used during training: - learningrate: 5e-06 - trainbatchsize: 1 - evalbatchsize: 8 - distributedtype: multi-GPU - numdevices: 8 - gradientaccumulationsteps: 8 - totaltrainbatchsize: 64 - totalevalbatchsize: 64 - lrschedulertype: cosine - lrschedulerwarmupsteps: 0.1 - numepochs: 3.0 - Transformers 5.2.0 - Pytorch 2.10.0 - Datasets 4.0.0 - Tokenizers 0.22.2
Moondream 3.1 is a vision language model with a mixture-of-experts architecture (9B total parameters, 2B active). It delivers state-of-the-art visual reasoning and detection while staying fast and cheap to deploy. Skills include query, detect, point, and caption, all native and all returning structured output. For the full story on what's new — including how we trained it and how it holds up on your own tasks — see the release notes. Photon is Moondream's high-performance inference engine. It runs the model locally on NVIDIA GPUs (Ampere or newer) and Apple Silicon Macs, with the same API as Moondream Cloud. No API key is required to run the base model locally. (You'll only need one to run…
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance. Qwen3.5 represents a significant leap forward, integrating breakthroughs in multimodal learning, architectural efficiency, reinforcement learning scale, and global accessibility to empower developers and enterprises with unprecedented capability and efficiency. For more details, please refer to our blog post Qwen3.5. WMT24++: a harder subset of WMT24 after difficulty labeling and rebalancing; we report the averaged scores on 55 languages using XCOMET-XXL. Empty cells (--) indicate scores not yet available or not applicable. Empty cells (--) indicate scores not…
This repo quantizes the model using data-free quantization technique. As of 2026-02-25, make sure your system has cuda12.8 installed. Then, create a fresh Python environment (e.g. python3.12 venv) and run: Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance. Qwen3.5 represents a significant leap forward, integrating breakthroughs in multimodal learning, architectural efficiency, reinforcement learning scale, and global accessibility to empower developers and enterprises with unprecedented capability and efficiency. For more details, please refer to our blog post Qwen3.5. WMT24++: a harder subset of WMT24 after…