Ollama · smallthinker

![image.png](/assets/library/smallthinker/1d25cb29-e27d-492c-be53-ce79b20def5b) A new model fine-tuned from the Qwen2.5-3b-Instruct model. SmallThinker is designed for the following use cases: * Edge…

ollama/smallthinker

![image.png](/assets/library/smallthinker/1d25cb29-e27d-492c-be53-ce79b20def5b)

A new model fine-tuned from the Qwen2.5-3b-Instruct model.

SmallThinker is designed for the following use cases:

* Edge Deployment: Its small size makes it ideal for deployment on resource-constrained devices. * Draft Model for QwQ-32B-Preview: SmallThinker can serve as a fast and efficient draft model for the larger QwQ-32B-Preview model, yielding a 70% speedup.

For achieving reasoning capabilities, it's crucial to generate long chains of COT reasoning. Therefore, based on QWQ-32B-Preview, the authors used various synthetic techniques(such as personahub) to create the QWQ-LONGCOT-500K dataset. Compared to other similar datasets, over 75% of the author's samples have output tokens exceeding 8K. To encourage research in the open-source community, the dataset was also made publicly available.

## References

[Hugging Face](https://huggingface.co/PowerInfer/SmallThinker-3B-Preview)

Specifications & capabilities

Published model ID
smallthinker

Deployments & artifacts

1–5 / 5

ollama

source id
ollama
execution mode
local
parameter size
3.4B
parameter count
3400000000
parameter count is approximate
true
quantization level
Q8_0
context window
32000
context window is approximate
true
artifact size bytes
3616094773
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
3.4B
parameter count
3400000000
parameter count is approximate
true
quantization level
F16
context window
32000
context window is approximate
true
artifact size bytes
6800652853
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
3.4B
parameter count
3400000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
32000
context window is approximate
true
artifact size bytes
2104939061
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
3.4B
parameter count
3400000000
parameter count is approximate
true
quantization level
Q8_0
context window
32000
context window is approximate
true
artifact size bytes
3616094773
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
3.4B
parameter count
3400000000
parameter count is approximate
true
quantization level
Q8_0
context window
32000
context window is approximate
true
artifact size bytes
3616094773
updated at
2026-11-16T08:10:06.079865+00:00

Original sources

1–2 / 2

Ollama · Model page ↗

Ollama · Catalog ↗

Source links

1–1 / 1

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace