---
license: apache-2.0
base_model: Qwen/Qwen3.5-4B
library_name: transformers
pipeline_tag: image-text-to-text
tags:
  - vision-language
  - tool-calling
  - agent
  - qwen3_5
  - local-agents
  - edge
---

![Karti-Small-VL-4B — it knows when it can't read something](./assets/karti-small-vl-4b.svg)

# Karti-Small-VL-4B · v1

**A 4B vision model that knows when it can't read something.**

Built for local agents that look at a thing and then call a tool about it — read
a panel, check a camera frame, act on a screen. The failure that matters there
isn't a wrong caption; it's a **confidently invented identifier**. v1 is trained
to hit that boundary and decline instead.

| | |
|---|---|
| Parameters | 4.66 B (4,659,865,088) |
| Base | [`Qwen/Qwen3.5-4B`](https://huggingface.co/Qwen/Qwen3.5-4B) @ `851bf6e8` |
| Precision | BF16 · 9.3 GB · merged weights, no adapter |
| Context | 32,768 |
| Tools | native, `qwen3_xml` parser |
| Faster build | [NVFP4](https://huggingface.co/KartiOS/Karti-Small-VL-4B-NVFP4) — 2.5×, Blackwell only |

## Results

![v1 against the untrained base](./assets/karti-vl-4b-results.svg)

Same endpoint, same rows, same decode path.

| | base | **v1** |
|---|---|---|
| **Invented-identifier rate** | 0.378 | **0.023** — 16× fewer |
| Panel reading | 0.595 | **0.967** |
| GUI grounding, ScreenSpot-v2 · n=1271 | 0.718 | **0.907** |
| ⤷ small targets · n=426 | 0.580 | **0.883** |
| Unparseable click points | 48/1272 | **9/1272** |
| General vision, curated · n=220 | 0.727 | **0.732** |
| False-refusal, real photos · n=600 | 0.220 | 0.227 |

ScreenSpot-v2 and the general-vision slice were **held out**. On the two hardest
abstention families the base scored zero; v1 scores 101/112 and 117/119.

**Scope, honestly:** part of the grounding gain is learning the normalised
0–1000 coordinate convention shared with the training set — real, but not "38%
better at seeing UI". And v1 reads *photographs* no better than the base; what
changed is that it stops over-refusing them. The legibility gain is on rendered
panels and screens.

## Speed — NVIDIA DGX Spark (GB10)

vLLM 0.27.1, BF16, 32k context, FP8 KV cache, temperature 0, single stream.

| tokens | tok/s |
|---|---|
| 128 | 21.0 |
| 512 | 21.1 |

Fits in ~20 GB. For 2.5× throughput at 3.7 GB, use the
[NVFP4 build](https://huggingface.co/KartiOS/Karti-Small-VL-4B-NVFP4) (needs
Blackwell, sm_120+).

## Use

```python
from transformers import AutoProcessor, AutoModelForImageTextToText

m = AutoModelForImageTextToText.from_pretrained(
    "KartiOS/Karti-Small-VL-4B", dtype="auto", device_map="auto")
p = AutoProcessor.from_pretrained("KartiOS/Karti-Small-VL-4B")
```

```bash
vllm serve KartiOS/Karti-Small-VL-4B \
  --max-model-len 32768 --kv-cache-dtype fp8 \
  --enable-auto-tool-choice --tool-call-parser qwen3_xml \
  --default-chat-template-kwargs '{"enable_thinking": false}'
```

Pin a revision — `main` moves. `revision="pre-v1"` is the untrained baseline.

## How it was trained

BF16 LoRA (r16, α32, lr 5e-5, 75 steps) merged into these weights. 32.5 M
trainable parameters across 248 language modules; the **vision tower is frozen
and proven frozen** — all 297 vision tensors are byte-identical to the base.

Corpus: 3,569 rows — an authored legibility ladder that places text exactly at
the readable/unreadable boundary, plus VizWiz and GUI-Odyssey.

The decisive parameter was **the share of the corpus whose answer is "I can't
read this."** At 29.1% the model learns the word, not the judgement: 0.955 on the
lane, then refusing 14 of 22 answerable photographs. At 14.4% it learns the
judgement. That threshold — not the learning rate, not the step count — is what
made v1 work.

> **Serve the merged weights, not a LoRA adapter.** vLLM 0.27.1 applies this
> adapter incompletely — about 0.19 absolute ScreenSpot accuracy, silently.
> Qwen3.5 packs its linear-attention projections and this adapter targets those
> sub-modules. The adapter is not published for that reason.

---

From [Lumbridge](https://lumbridgecorp.com/models). Sibling text model:
[`Karti-Small-RSI-3B`](https://huggingface.co/KartiOS/Karti-Small-RSI-3B).