Which Ollama Local Model is Best? Pineapple SVG Comparison (14 Models)
After testing models on sunflowers and mechanical scenes, we turned to another Fibonacci marvel of nature: the pineapple. A pineapple’s skin is covered in hexagonal scales that form three sets of spirals – each following Fibonacci numbers (typically 8, 13, and 21). This prompt tests whether models can render that textured skin pattern, the crown of spiky leaves on top, the golden-yellow color gradient of ripe flesh, and the overall oval shape that makes a pineapple instantly recognizable.
The prompt was: Make an svg image of a pineapple
This is the twelfth in our SVG benchmark series. See also: duck on a bicycle, duck with a parachute, duck driving a jeep, cherry blossom trees, duck programmer debugging at 3am, baby shark fish, octopus playing chess, FIFA World Cup 2026, elephant on a skateboard, flying helicopter, sunflower with seeds, pinecone, nautilus shell, dates palm tree.
Why a pineapple? The pineapple prompt is a texture and pattern stress test because it combines: (1) Fibonacci diagonal spirals – the hexagonal scales on a pineapple skin form three intersecting spiral sets (8, 13, 21), and a model with mathematical intuition should attempt a diamond or hexagonal grid pattern rather than a flat oval, (2) Crown leaves – a pineapple has a distinctive crown of stiff green spiky leaves on top; omitting it makes the drawing unrecognizable, (3) Color gradient – a ripe pineapple transitions from green near the top to golden-yellow at the bottom, (4) Oval body shape – the body is an elongated oval, not a circle or rectangle, (5) Texture density – a real pineapple has dozens of scale segments; the model must balance detail with file size, and (6) Symmetry – the body is bilaterally symmetric, while the crown leaves radiate from the top.
The goal is not to declare a winner – it is to give you the data so you can pick the best model for your own use case. We show you the SVG, the stats, and a short analysis for each. You decide.
How to Choose the Best Ollama Model for Pineapple SVGs
The pineapple prompt rewards different things than previous prompts. Here are the criteria to use:
- Skin texture pattern: Does the model render the diamond/hexagonal scale pattern on the skin? Or is it just a flat oval? The Fibonacci spiral pattern is the ultimate test.
- Crown of leaves: Does it include the green spiky crown on top? How many leaves? Are they individually drawn or just suggested?
- Color gradient: Does it use a green-to-yellow gradient on the body? Or flat color?
- Body shape: Is the body an oval (taller than wide)? Or a circle/rectangle?
- Scale detail: Does each scale have a subtle 3D shading or highlight? Or are they flat diamonds?
- Overall recognizability: If you showed this SVG to someone, would they immediately say “pineapple”?
- SVG code quality: Does it use
<pattern>,<defs>, or<use>to efficiently generate the repeating scale texture?
How It Works
The script discovers all locally installed models via the Ollama API (/api/tags), then sends the identical prompt through the OpenAI-compatible endpoint (http://localhost:11434/v1/chat/completions). Each model’s response is parsed for an <svg>...</svg> block, and the extracted SVG is saved for rendering with minimal post-processing (adding width="100%" height="auto" for responsive embedding and fixing XML errors so the SVG renders in browsers).
Unlike our cloud model benchmarks, these models run entirely on the local GPU – no cloud subscription or network round-trip required. This means generation times reflect local hardware performance, and model sizes range from 1B to 31B parameters. Embedding, vision, and OCR models are automatically skipped.
Summary Table: Compare All Models at a Glance
Use this table to quickly compare models on the metrics that matter. The verdict column is a one-line summary to help you shortlist – but read the per-model sections below for the full picture before you decide.
| # | Model | SVG Size | Shapes | Colors | Complexity | Verdict |
|---|---|---|---|---|---|---|
| 1 | cieloforge/qwen2.5-14B-instruct-spec:latest | 394 | 3 | 2 | Compact | Compact |
| 2 | deepseek-r1:1.5b | 359 | 2 | 4 | Compact | Compact |
| 3 | deepseek-r1:7b | 1047 | 8 | 3 | Compact | Compact |
| 4 | gemma3:1b-it-qat | 761 | 5 | 2 | Compact | Compact |
| 5 | gemma3:4b | 729 | 7 | 5 | Compact | Compact |
| 6 | gemma4:12b | 1803 | 12 | 6 | Compact | Compact |
| 7 | gemma4:26b-a4b-it-qat | 1486 | 21 | 6 | Compact | Compact |
| 8 | lfm2.5:latest | 618 | 6 | 4 | Compact | Compact |
| 9 | llama3.1:8b | 577 | 1 | 1 | Compact | Compact |
| 10 | qwen2.5-coder-14b:latest | 517 | 2 | 3 | Compact | Compact |
| 11 | qwen2.5-coder:7b | 519 | 5 | 5 | Compact | Compact |
| 12 | qwen2.5:7b | 574 | 6 | 5 | Compact | Compact |
| 13 | qwen3.5:9b | 2266 | 17 | 6 | Medium | Balanced |
| 14 | qwen3.5:latest | 3975 | 4 | 4 | Compact | Compact |
| 15 | gemma4:31b-it-qat | - | - | - | - | Failed |
| 16 | gemma4:latest | - | - | - | - | Failed |
| 17 | jeffgreen311/Eve-V2-Unleashed-Qwen3.5-8B-Liberated-4K-4B-Merged:latest | - | - | - | - | Failed |
| 18 | kwangsuklee/Qwen3.5-9B.Q4_K_M-Claude-4.6-Opus-Reasoning-Distilled-v2:latest | - | - | - | - | Failed |
| 19 | qwen2.5:3b | - | - | - | - | Failed |
| 20 | qwen3.5:4b | - | - | - | - | Failed |
| 21 | qwen3:14b | - | - | - | - | Failed |
| 22 | qwen3:8b | - | - | - | - | Failed |
| 23 | SetneufPT/Qwen3.6-27B-MTP_Q3_32K_16GB-GPU:latest | - | - | - | - | Failed |
| 24 | SetneufPT/Qwen3.6-27B.MTP_Q3_32K_16GB-GPU:latest | - | - | - | - | Failed |
| 25 | VladimirGav/Qwen3.6-27B-16GB-VRAM-Uncensored:latest | - | - | - | - | Failed |
14 out of 25 models produced a valid SVG. The 11 that failed either returned an error or did not include a valid <svg>...</svg> block in their response.
Quick Recommendation by Use Case
If you just want a shortcut, here is which model to pick based on what you care about:
- You want the most accurate Fibonacci skin pattern: look for models whose SVG shows a visible diamond/hexagonal grid on the body
- You want the most visually rich pineapple: pick models labeled “Very high” complexity in the table above
- You want a recognizable pineapple with a crown: check the per-model analysis for crown leaf presence
- You want gradient coloring (green to gold): look for models that used
<linearGradient>on the body - You want efficient code for the repeating pattern: look for models that used
<pattern>or<use>elements - You want a balance of detail and speed: pick models labeled “Balanced” or “Detailed”
Now read on for the full per-model breakdown and judge for yourself.
1. cieloforge/qwen2.5-14B-instruct-spec:latest
SVG size: 394 characters
Complexity: Compact
Shape elements: 3
Distinct colors: 2
Raw response: 639 characters
Generation time: 39.8s
Analysis
This SVG contains approximately 3 shape elements and uses 2 distinct colors.
Notable SVG techniques used:
- Uses
<defs>blocks for reusable components (a sign of well-structured, editable SVG) - Uses
<use>references to reuse defined elements – ideal for repeating motifs like seeds, scales, or leaflets
This is a compact SVG (under 5,000 characters) that uses minimal markup to convey the scene. The model prioritized efficiency and simplicity over elaborate detail. View raw SVG source
```xml ```
2. deepseek-r1:1.5b
SVG size: 359 characters
Complexity: Compact
Shape elements: 2
Distinct colors: 4
Raw response: 631 characters
Generation time: 44.2s
Analysis
This SVG contains approximately 2 shape elements and uses 4 distinct colors.
Notable SVG techniques used:
- Uses standard SVG primitives (rect, circle, path, polygon) to compose the scene
This is a compact SVG (under 5,000 characters) that uses minimal markup to convey the scene. The model prioritized efficiency and simplicity over elaborate detail. View raw SVG source
```xml ```
3. deepseek-r1:7b
SVG size: 1047 characters
Complexity: Compact
Shape elements: 8
Distinct colors: 3
Raw response: 1723 characters
Generation time: 24.3s
Analysis
This SVG contains approximately 8 shape elements and uses 3 distinct colors.
Notable SVG techniques used:
- Contains XML comments, showing the model’s internal documentation of its work
This is a compact SVG (under 5,000 characters) that uses minimal markup to convey the scene. The model prioritized efficiency and simplicity over elaborate detail. View raw SVG source
```xml ```
4. gemma3:1b-it-qat
SVG size: 761 characters
Complexity: Compact
Shape elements: 5
Distinct colors: 2
Raw response: 3348 characters
Generation time: 43.9s
Analysis
This SVG contains approximately 5 shape elements and uses 2 distinct colors.
Notable SVG techniques used:
- Contains XML comments, showing the model’s internal documentation of its work
This is a compact SVG (under 5,000 characters) that uses minimal markup to convey the scene. The model prioritized efficiency and simplicity over elaborate detail. View raw SVG source
```xml ```
5. gemma3:4b
SVG size: 729 characters
Complexity: Compact
Shape elements: 7
Distinct colors: 5
Raw response: 3861 characters
Generation time: 75.2s
Analysis
This SVG contains approximately 7 shape elements and uses 5 distinct colors.
Notable SVG techniques used:
- Uses Bezier curves (
C,Q,Apath commands) for smooth organic shapes - Contains XML comments, showing the model’s internal documentation of its work
This is a compact SVG (under 5,000 characters) that uses minimal markup to convey the scene. The model prioritized efficiency and simplicity over elaborate detail. View raw SVG source
```xml ```
6. gemma4:12b
SVG size: 1803 characters
Complexity: Compact
Shape elements: 12
Distinct colors: 6
Raw response: 2184 characters
Generation time: 133.9s
Analysis
This SVG contains approximately 12 shape elements and uses 6 distinct colors.
Notable SVG techniques used:
- Uses Bezier curves (
C,Q,Apath commands) for smooth organic shapes - Contains XML comments, showing the model’s internal documentation of its work
This is a compact SVG (under 5,000 characters) that uses minimal markup to convey the scene. The model prioritized efficiency and simplicity over elaborate detail. View raw SVG source
```xml ```
7. gemma4:26b-a4b-it-qat
SVG size: 1486 characters
Complexity: Compact
Shape elements: 21
Distinct colors: 6
Raw response: 2561 characters
Generation time: 258.6s
Analysis
This SVG contains approximately 21 shape elements and uses 6 distinct colors.
Notable SVG techniques used:
- Uses Bezier curves (
C,Q,Apath commands) for smooth organic shapes - Contains XML comments, showing the model’s internal documentation of its work
This is a compact SVG (under 5,000 characters) that uses minimal markup to convey the scene. The model prioritized efficiency and simplicity over elaborate detail. View raw SVG source
```xml ```
8. lfm2.5:latest
SVG size: 618 characters
Complexity: Compact
Shape elements: 6
Distinct colors: 4
Raw response: 1189 characters
Generation time: 419.9s
Analysis
This SVG contains approximately 6 shape elements and uses 4 distinct colors.
Notable SVG techniques used:
- Uses Bezier curves (
C,Q,Apath commands) for smooth organic shapes - Contains XML comments, showing the model’s internal documentation of its work
This is a compact SVG (under 5,000 characters) that uses minimal markup to convey the scene. The model prioritized efficiency and simplicity over elaborate detail. View raw SVG source
```xml ```
9. llama3.1:8b
SVG size: 577 characters
Complexity: Compact
Shape elements: 1
Distinct colors: 1
Raw response: 1405 characters
Generation time: 153.5s
Analysis
This SVG contains approximately 1 shape elements and uses 1 distinct colors.
Notable SVG techniques used:
- Uses Bezier curves (
C,Q,Apath commands) for smooth organic shapes
This is a compact SVG (under 5,000 characters) that uses minimal markup to convey the scene. The model prioritized efficiency and simplicity over elaborate detail. View raw SVG source
```xml ```
10. qwen2.5-coder-14b:latest
SVG size: 517 characters
Complexity: Compact
Shape elements: 2
Distinct colors: 3
Raw response: 688 characters
Generation time: 186.5s
Analysis
This SVG contains approximately 2 shape elements and uses 3 distinct colors.
Notable SVG techniques used:
- Uses
<defs>blocks for reusable components (a sign of well-structured, editable SVG) - Includes gradient fills for richer visual depth
- Uses Bezier curves (
C,Q,Apath commands) for smooth organic shapes
This is a compact SVG (under 5,000 characters) that uses minimal markup to convey the scene. The model prioritized efficiency and simplicity over elaborate detail. View raw SVG source
```xml ```
11. qwen2.5-coder:7b
SVG size: 519 characters
Complexity: Compact
Shape elements: 5
Distinct colors: 5
Raw response: 2512 characters
Generation time: 183.4s
Analysis
This SVG contains approximately 5 shape elements and uses 5 distinct colors.
Notable SVG techniques used:
- Uses Bezier curves (
C,Q,Apath commands) for smooth organic shapes - Contains XML comments, showing the model’s internal documentation of its work
This is a compact SVG (under 5,000 characters) that uses minimal markup to convey the scene. The model prioritized efficiency and simplicity over elaborate detail. View raw SVG source
```xml ```
12. qwen2.5:7b
SVG size: 574 characters
Complexity: Compact
Shape elements: 6
Distinct colors: 5
Raw response: 1317 characters
Generation time: 148.6s
Analysis
This SVG contains approximately 6 shape elements and uses 5 distinct colors.
Notable SVG techniques used:
- Uses Bezier curves (
C,Q,Apath commands) for smooth organic shapes - Contains XML comments, showing the model’s internal documentation of its work
This is a compact SVG (under 5,000 characters) that uses minimal markup to convey the scene. The model prioritized efficiency and simplicity over elaborate detail. View raw SVG source
```xml ```
13. qwen3.5:9b
SVG size: 2266 characters
Complexity: Medium
Shape elements: 17
Distinct colors: 6
Raw response: 2306 characters
Generation time: 131.3s
Analysis
This SVG contains approximately 17 shape elements and uses 6 distinct colors.
Notable SVG techniques used:
- Uses transforms (translate, rotate, scale) for precise positioning and rotation
- Uses Bezier curves (
C,Q,Apath commands) for smooth organic shapes - Contains XML comments, showing the model’s internal documentation of its work
This is a compact SVG (under 5,000 characters) that uses minimal markup to convey the scene. The model prioritized efficiency and simplicity over elaborate detail. View raw SVG source
```xml ```
14. qwen3.5:latest
SVG size: 3975 characters
Complexity: Compact
Shape elements: 4
Distinct colors: 4
Raw response: 5173 characters
Generation time: 363.2s
Analysis
This SVG contains approximately 4 shape elements and uses 4 distinct colors.
Notable SVG techniques used:
- Uses
<defs>blocks for reusable components (a sign of well-structured, editable SVG) - Uses
<pattern>elements for repeating textures (e.g., pineapple skin or trunk scars) - Includes gradient fills for richer visual depth
- Uses transforms (translate, rotate, scale) for precise positioning and rotation
- Uses Bezier curves (
C,Q,Apath commands) for smooth organic shapes - Contains XML comments, showing the model’s internal documentation of its work
This is a compact SVG (under 5,000 characters) that uses minimal markup to convey the scene. The model prioritized efficiency and simplicity over elaborate detail. Enjoyed this post? Never miss out on future posts by following us View raw SVG source
```xml 
