Instructions to use simoneschiavoi/VisionPsy-Nano-DomCal with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use simoneschiavoi/VisionPsy-Nano-DomCal with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf simoneschiavoi/VisionPsy-Nano-DomCal:Q4_0
# Run inference directly in the terminal:
llama cli -hf simoneschiavoi/VisionPsy-Nano-DomCal:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf simoneschiavoi/VisionPsy-Nano-DomCal:Q4_0
# Run inference directly in the terminal:
llama cli -hf simoneschiavoi/VisionPsy-Nano-DomCal:Q4_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf simoneschiavoi/VisionPsy-Nano-DomCal:Q4_0
# Run inference directly in the terminal:
./llama-cli -hf simoneschiavoi/VisionPsy-Nano-DomCal:Q4_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf simoneschiavoi/VisionPsy-Nano-DomCal:Q4_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf simoneschiavoi/VisionPsy-Nano-DomCal:Q4_0

Use Docker

docker model run hf.co/simoneschiavoi/VisionPsy-Nano-DomCal:Q4_0

LM Studio
Jan
Ollama
How to use simoneschiavoi/VisionPsy-Nano-DomCal with Ollama:
```
ollama run hf.co/simoneschiavoi/VisionPsy-Nano-DomCal:Q4_0
```

Unsloth Studio

How to use simoneschiavoi/VisionPsy-Nano-DomCal with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for simoneschiavoi/VisionPsy-Nano-DomCal to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for simoneschiavoi/VisionPsy-Nano-DomCal to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for simoneschiavoi/VisionPsy-Nano-DomCal to start chatting

Docker Model Runner
How to use simoneschiavoi/VisionPsy-Nano-DomCal with Docker Model Runner:
```
docker model run hf.co/simoneschiavoi/VisionPsy-Nano-DomCal:Q4_0
```

Lemonade

How to use simoneschiavoi/VisionPsy-Nano-DomCal with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull simoneschiavoi/VisionPsy-Nano-DomCal:Q4_0

Run and chat with the model

lemonade run user.VisionPsy-Nano-DomCal-Q4_0

List all available models

lemonade list

Atomic Chat

VisionPsy-Nano-DomCal / README.md

simoneschiavoi

Move artifact hashes into SHA256SUMS reference file

e61a7fe verified 3 days ago

preview code

Raw

History Blame Contribute Delete

6.43 kB

	---
	base_model: qvac/VisionPsy-Nano-460M
	base_model_relation: quantized
	license: apache-2.0
	language:
	- en
	tags:
	- vision-language-model
	- gguf
	- quantization
	- llama.cpp
	---

	# VisionPsy-Nano DomCal

	The q4_0 envelope, repaired at zero measured cost: 12W/4L/1T over 17 descriptive rows vs same-harness QVAC q4_0 — pooled +2.2 points (p = 4.7×10⁻⁵) — and 2W/15L/0T over 17 displayed rows vs QVAC q4_k_m-imat (same-harness re-run) at −44.6 MiB (−11.4%).

	A GGUF quantized derivative of QVAC's [VisionPsy-Nano-460M](https://huggingface.co/qvac/VisionPsy-Nano-460M) built with P1 (domcal) — domain-calibrated imatrix quantization. This is not a new trained checkpoint: the ~460M-parameter architecture (SigLIP2 vision encoder + SmolLM2-360M backbone) is unchanged; only the quantization calibration was modified. Part of the VisionPsy-Nano release collection — see the Links section below.

	## Exact runtime pair

	\| Component \| File \| Bytes \|
	\|---\|---\|---:\|
	\| LM \| `visionpsy-nano-460m-q4_0-domcal.gguf` \| 256379776 \|
	\| mmproj \| `mmproj-visionpsy-nano-460m-q8.gguf` \| 108782144 \|

	Package size: 348.2 MiB. Use only this LM/mmproj mapping. SHA-256 checksums for both files ship in this repository as [SHA256SUMS](https://huggingface.co/simoneschiavoi/VisionPsy-Nano-DomCal/blob/main/SHA256SUMS) — verify after download with `sha256sum -c SHA256SUMS`.

	## Model at a glance

	\| \| \|
	\|---\|---\|
	\| Base model \| QVAC VisionPsy-Nano-460M (~460M parameters; SigLIP2 vision encoder + SmolLM2-360M backbone) \|
	\| Technique \| P1 (domcal) — importance matrix computed on a domain-matched corpus, steering q4_0 rounding toward the tensors that matter for visual question answering \|
	\| Quantization \| q4_0 LM (same format as QVAC's baseline) + QVAC's own q8 mmproj — same size class as the base \|
	\| Calibration data \| VQAv2-train + TextVQA-train, ChatML-formatted; training splits only — never benchmark test data, no evaluation images \|
	\| Total size \| 348.2 MiB = 244.5 MiB LM + 103.7 MiB mmproj — +0.5 MiB vs QVAC q4_0 (347.7), −44.6 MiB (−11.4%) vs QVAC q4_k_m-imat (392.8) \|
	\| Headline \| 12W/4L/1T over 17 descriptive rows vs same-harness QVAC q4_0; 9W/4L/1T over 14 non-selection rows; normalized 60.31 vs q4_0's 59.48; 2W/15L/0T over 17 displayed rows vs QVAC q4_k_m-imat (same-harness re-run) \|
	\| Observed speed \| 802.2 ms/item vs q4_0's 803.5 — repair at zero measured latency cost (−1.3 ms/item) \|

	## Why this build exists

	The study's core finding: a label like "4-bit" says how many bits are available, not whether those bits protect the tensors that matter for the model's actual job. Domain calibration is a targeted repair, not a universal upgrade. Applied to QVAC's uncalibrated q4_0 build, it recovered a pooled +2.2 points (p = 4.7×10⁻⁵) — the largest single-technique gain measured in the campaign. The same idea applied to QVAC's already-calibrated q4_k_m did not stack, and at 5-bit it actively hurt (strict OCR −2.2, p = 0.003): calibration matters most where importance information is missing. DomCal is that finding, shipped: the repair applied exactly where it helps.

	## Vs the two rulers

	The primary ruler is QVAC q4_k_m-imat, QVAC's flagship build — re-run in this same harness with a hash-pinned full-17 record (judged rows scored with a qwen3.6-27b API judge, a reconstruction of QVAC's judging protocol validated within ±1 pt of their published card on 6/8 judged benchmarks; QVAC's own card numbers remain labeled context, never medaled). QVAC q4_0 is the secondary same-harness ruler. Negative deltas = smaller/faster.

	\| \| QVAC q4_k_m-imat (same-harness re-run) \| QVAC q4_0 (same-harness) \|
	\|---\|---:\|---:\|
	\| W/L/T over 17 displayed rows \| 2W/15L/0T \| 12W/4L/1T (17 descriptive rows) \|
	\| Package size Δ (348.2 MiB) \| −44.6 MiB (−11.4%) \| +0.5 MiB \|
	\| Speed Δ (802.2 ms/item) \| −11.0 ms/item (−1.4%) \| −1.3 ms/item \|

	## Measured results

	Strongest gains land exactly where the uncalibrated build was weakest: MMStar 45.8 vs 42.3, MMBench 58.1 vs 55.0, MathVista 43.9 vs 41.7 against the q4_0 control. The named losses stay visible: QVAC q4_0 keeps MME, POPE and RealWorldQA; MMMU is tied. Against the flagship imat build, DomCal posts an honest 2W/15L/0T — imat keeps OCRBench, DocVQA, ChartQA and InfoVQA. This is the same-format repair of the q4_0 baseline and a smaller, faster alternative to the flagship — not an imat-beater.

	## Limitations

	- Exploratory scope: one seed (17), one harness, one GPU. Counts are descriptive rows, not statistical proof or universal-superiority claims; the pooled +2.2-point repair against q4_0 is the pre-registered significance claim (p = 4.7×10⁻⁵).
	- Judged rows: qwen3.6-27b via OpenRouter — an attempted same-model reconstruction of QVAC's judge, not their exact serving protocol.
	- Calibration scope: benefits demonstrated on the uncalibrated q4_0 base; the technique is not additive on already-calibrated builds.
	- A completed post-hoc contamination audit of the calibration corpus is summarized in the release ledger ([release repository](https://github.com/simoneschiavoi/visionpsy-optimization)).

	## Links

	This model is one of four verified VisionPsy-Nano GGUF packages released together under the [simoneschiavoi Hugging Face namespace](https://huggingface.co/simoneschiavoi).

	- Project website (full interactive research write-up): <https://simoneschiavoi.github.io/visionpsy-optimization/>
	- Benchmarks (full same-harness ledger, all models × 17 benchmarks): <https://simoneschiavoi.github.io/visionpsy-optimization/#benchmarks>
	- Hugging Face namespace (all four packages): <https://huggingface.co/simoneschiavoi>
	- Sibling models:
	- [VisionPsy-Nano DomCal-Slim](https://huggingface.co/simoneschiavoi/VisionPsy-Nano-DomCal-Slim)
	- [VisionPsy-Nano DomCal-EmbGuard](https://huggingface.co/simoneschiavoi/VisionPsy-Nano-DomCal-EmbGuard)
	- [VisionPsy-Nano TriStack](https://huggingface.co/simoneschiavoi/VisionPsy-Nano-TriStack)

	## License and attribution

	Apache-2.0 derivative. The Apache-2.0 NOTICE distributed with the artifact must be retained, and QVAC's VisionPsy-Nano-460M must be attributed as the base model. Build evidence, evaluation ledger, and reproduction scripts: <https://github.com/simoneschiavoi/visionpsy-optimization>. All four release packages: <https://huggingface.co/simoneschiavoi>.