Which Ollama Local Model is Best? Pinecone SVG Comparison (15 Models)

Continuing our Fibonacci series, we asked our models to draw a pinecone – one of nature’s most striking examples of Fibonacci spirals. A pinecone’s scales spiral outward from the base in two directions, with the number of spirals in each direction typically being consecutive Fibonacci numbers (like 5 and 8, or 8 and 13). This prompt tests whether models can render that spiral scale pattern, the overall elongated egg shape, the woody brown color palette, and the 3D depth that makes each scale appear to overlap the one below it.

The prompt was: Make an svg image of a pinecone

This is the thirteenth 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, pineapple, nautilus shell, dates palm tree.

Why a pinecone? The pinecone prompt is a depth and spiral stress test because it combines: (1) Fibonacci spiral scales – the scales spiral outward in two directions following Fibonacci numbers; a model with mathematical intuition should attempt overlapping scale patterns rather than flat stripes, (2) 3D depth via overlap – each scale overlaps the one below it, creating a sense of depth; this requires careful z-ordering and shape layering, (3) Egg shape – a pinecone is an elongated egg/oval, rounded at the base and pointed at the top, (4) Woody texture – the scales have a matte brown color with subtle shading, (5) Scale geometry – each scale is a curved diamond or teardrop shape, not a simple rectangle, and (6) Density vs. readability – a real pinecone has many scales; the model must decide how many to draw while keeping the SVG file manageable.

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 Pinecone SVGs

The pinecone prompt rewards different things than previous prompts. Here are the criteria to use:

• Spiral scale pattern: Does the model arrange scales in visible spiral patterns? Or just rows/columns? True Fibonacci spirals are the gold standard.
• 3D depth and overlap: Do the scales overlap each other to create depth? Or are they flat side-by-side?
• Overall shape: Is the body an elongated egg shape? Or a circle/cylinder?
• Scale geometry: Are the scales curved diamonds or teardrops? Or simple rectangles/triangles?
• Color palette: Does it use woody brown tones with shading? Or flat single color?
• Recognizability: Would someone immediately recognize this as a pinecone?
• SVG code quality: Does it use <defs>, <use>, and transforms to efficiently generate repeating scales?

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	643	4	3	Compact	Compact
2	deepseek-r1:1.5b	2671	6	3	Compact	Compact
3	deepseek-r1:7b	873	3	1	Compact	Compact
4	gemma3:1b-it-qat	265	2	2	Compact	Compact
5	gemma3:4b	620	6	7	Compact	Compact
6	gemma4:12b	1735	19	5	Compact	Compact
7	gemma4:26b-a4b-it-qat	3181	4	12	Compact	Compact
8	lfm2.5:latest	1247	6	4	Compact	Compact
9	llama3.1:8b	511	3	2	Compact	Compact
10	qwen2.5-coder:7b	346	2	1	Compact	Compact
11	qwen2.5:3b	271	3	2	Compact	Compact
12	qwen2.5:7b	611	5	4	Compact	Compact
13	qwen3.5:4b	1002	7	5	Compact	Compact
14	qwen3.5:9b	170	0	0	Compact	Compact
15	qwen3.5:latest	3076	20	17	Medium	Balanced
16	gemma4:31b-it-qat	-	-	-	-	Failed
17	gemma4:latest	-	-	-	-	Failed
18	jeffgreen311/Eve-V2-Unleashed-Qwen3.5-8B-Liberated-4K-4B-Merged:latest	-	-	-	-	Failed
19	kwangsuklee/Qwen3.5-9B.Q4_K_M-Claude-4.6-Opus-Reasoning-Distilled-v2:latest	-	-	-	-	Failed
20	qwen2.5-coder-14b:latest	-	-	-	-	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

15 out of 25 models produced a valid SVG. The 10 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 spiral scales: look for models whose SVG shows visible spiral patterns in the scale arrangement
• You want 3D depth with overlapping scales: check the per-model analysis for overlap and z-ordering
• You want the most detailed pinecone: pick models labeled “Very high” complexity in the table above
• You want efficient repeating-scale code: look for models that used <use> and <defs> elements
• You want a small SVG for web embedding: pick models with “Compact” verdict
• 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: 643 characters
Complexity: Compact
Shape elements: 4
Distinct colors: 3
Raw response: 1452 characters
Generation time: 67.4s

Analysis

This SVG contains approximately 4 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 ```

2. deepseek-r1:1.5b

SVG size: 2671 characters
Complexity: Compact
Shape elements: 6
Distinct colors: 3
Raw response: 3328 characters
Generation time: 18.7s

Analysis

This SVG contains approximately 6 shape elements and uses 3 distinct colors.

Notable SVG techniques used:

• Uses Bezier curves (C, Q, A path 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 ```

3. deepseek-r1:7b

SVG size: 873 characters
Complexity: Compact
Shape elements: 3
Distinct colors: 1
Raw response: 1834 characters
Generation time: 57.4s

Analysis

This SVG contains approximately 3 shape elements and uses 1 distinct colors.

Notable SVG techniques used:

• Uses Bezier curves (C, Q, A path 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 ```

4. gemma3:1b-it-qat

SVG size: 265 characters
Complexity: Compact
Shape elements: 2
Distinct colors: 2
Raw response: 2558 characters
Generation time: 41.9s

Analysis

This SVG contains approximately 2 shape elements and uses 2 distinct colors.

Notable SVG techniques used:

• Uses Bezier curves (C, Q, A path 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 ```

5. gemma3:4b

SVG size: 620 characters
Complexity: Compact
Shape elements: 6
Distinct colors: 7
Raw response: 4273 characters
Generation time: 96.4s

Analysis

This SVG contains approximately 6 shape elements and uses 7 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 ```

6. gemma4:12b

SVG size: 1735 characters
Complexity: Compact
Shape elements: 19
Distinct colors: 5
Raw response: 2517 characters
Generation time: 156.4s

Analysis

This SVG contains approximately 19 shape elements and uses 5 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, A path 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: 3181 characters
Complexity: Compact
Shape elements: 4
Distinct colors: 12
Raw response: 4171 characters
Generation time: 303.3s

Analysis

This SVG contains approximately 4 shape elements and uses 12 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
• Includes gradient fills for richer visual depth
• Applies SVG filters (e.g., drop shadows, blurs) for atmospheric effects
• Uses transforms (translate, rotate, scale) for precise positioning and rotation
• Uses Bezier curves (C, Q, A path 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: 1247 characters
Complexity: Compact
Shape elements: 6
Distinct colors: 4
Raw response: 2207 characters
Generation time: 446.6s

Analysis

This SVG contains approximately 6 shape elements and uses 4 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 transforms (translate, rotate, scale) for precise positioning and rotation
• Uses Bezier curves (C, Q, A path 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: 511 characters
Complexity: Compact
Shape elements: 3
Distinct colors: 2
Raw response: 1168 characters
Generation time: 184.3s

Analysis

This SVG contains approximately 3 shape elements and uses 2 distinct colors.

Notable SVG techniques used:

• Uses Bezier curves (C, Q, A path 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 ```

10. qwen2.5-coder:7b

SVG size: 346 characters
Complexity: Compact
Shape elements: 2
Distinct colors: 1
Raw response: 768 characters
Generation time: 176.7s

Analysis

This SVG contains approximately 2 shape elements and uses 1 distinct colors.

Notable SVG techniques used:

• Uses Bezier curves (C, Q, A path 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 ```

11. qwen2.5:3b

SVG size: 271 characters
Complexity: Compact
Shape elements: 3
Distinct colors: 2
Raw response: 1214 characters
Generation time: 100.1s

Analysis

This SVG contains approximately 3 shape elements and uses 2 distinct colors.

Notable SVG techniques used:

• Uses Bezier curves (C, Q, A path 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 ```

12. qwen2.5:7b

SVG size: 611 characters
Complexity: Compact
Shape elements: 5
Distinct colors: 4
Raw response: 1440 characters
Generation time: 103.4s

Analysis

This SVG contains approximately 5 shape elements and uses 4 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 ```

13. qwen3.5:4b

SVG size: 1002 characters
Complexity: Compact
Shape elements: 7
Distinct colors: 5
Raw response: 1025 characters
Generation time: 186.3s

Analysis

This SVG contains approximately 7 shape elements and uses 5 distinct colors.

Notable SVG techniques used:

• Uses Bezier curves (C, Q, A path 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. qwen3.5:9b

SVG size: 170 characters
Complexity: Compact
Shape elements: 0
Distinct colors: 0
Raw response: 918 characters
Generation time: 216.1s

Analysis

This SVG contains approximately 0 shape elements and uses 0 distinct colors.

Notable SVG techniques used:

• Uses transforms (translate, rotate, scale) for precise positioning and rotation

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 ```

15. qwen3.5:latest

SVG size: 3076 characters
Complexity: Medium
Shape elements: 20
Distinct colors: 17
Raw response: 3118 characters
Generation time: 270.3s

Analysis

This SVG contains approximately 20 shape elements and uses 17 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
• Includes animation elements – the model attempted motion
• Uses Bezier curves (C, Q, A path 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 ```

Failed Models

The following 10 models did not produce a valid SVG (either returned an error or the response did not contain a parseable <svg>...</svg> block):

• gemma4:31b-it-qat – TimeoutError: timed out
• gemma4:latest – TimeoutError: timed out
• jeffgreen311/Eve-V2-Unleashed-Qwen3.5-8B-Liberated-4K-4B-Merged:latest – TimeoutError: timed out
• kwangsuklee/Qwen3.5-9B.Q4_K_M-Claude-4.6-Opus-Reasoning-Distilled-v2:latest – TimeoutError: timed out
• qwen2.5-coder-14b:latest – no SVG block in response
• qwen3:14b – TimeoutError: timed out
• qwen3:8b – TimeoutError: timed out
• SetneufPT/Qwen3.6-27B-MTP_Q3_32K_16GB-GPU:latest – TimeoutError: timed out
• SetneufPT/Qwen3.6-27B.MTP_Q3_32K_16GB-GPU:latest – TimeoutError: timed out
• VladimirGav/Qwen3.6-27B-16GB-VRAM-Uncensored:latest – TimeoutError: timed out

Conclusion

We asked 25 Ollama local models to draw a pinecone – a subject deeply connected to Fibonacci mathematics. The results reveal each model’s natural instinct for mathematical patterns, organic curves, and natural color palettes.

Key takeaways:

• Mathematical intuition varies widely: some models attempted Fibonacci spiral arrangements naturally, while others defaulted to simple grids or flat shapes. The models that attempted spirals demonstrate a deeper understanding of natural geometry.
• Detail and file size trade-off: models that produced the richest scenes (Very high complexity) also generated the largest SVG files. For web embedding, “Balanced” or “Detailed” models may be more practical.
• Color palettes differ dramatically: some models used sophisticated gradients and 15+ distinct colors, while others used as few as 4 flat colors. More colors generally means a more lifelike result.
• Code structure quality varies: the best models used <defs>, <use>, and <pattern> elements to efficiently generate repeating structures (seeds, scales, leaflets). This is a strong signal of model capability for practical SVG work.
• No single model is best at everything: the “right” model depends on whether you prioritize mathematical accuracy, visual beauty, file size, or code quality.

Try it yourself: run the benchmark script with your own prompt and see how the models perform on your specific use case. The full code is available in the ollama-svg-benchmark repository.

---

Which model do you think drew the best pinecone? Let us know in the comments below!

Enjoyed this post? Never miss out on future posts by following us