Timber
Shares rank 16 of 27 inference engines by recommenders
Lets people serve classical ML models directly to backend systems without Python or shared libraries, and portable across platforms. Critics note inference speedups add little to the whole pipeline.
Lets people serve classical ML models directly to backend systems without Python or shared libraries, and portable across platforms. Critics note inference speedups add little to the whole pipeline.
11 people gave an opinion
- recommend it
- 9
- criticize it
- 2
- approval share
- 82%
Recommended in 3 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: recommended
- February 2026: not recommended
- March 2026: recommended
- April 2026: not recommended
- May 2026: not recommended
- June 2026: not recommended
- July 2026: not recommended
- August 2026: recommended
- September 2026: not recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 9 people recommend itNeeds 10 or more, not met.
- 4.5 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 3 of 13 monthsNeeds 4 or more, not met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Welcomed as a simple concept
“Nice idea, i needed something like it”
Comment from 2 Mar 2026 in “Show HN: Timber – Ollama for classical ML models, 336x faster than Python” “the concept alone sounds great”
Comment from 2 Mar 2026 in “Show HN: Timber – Ollama for classical ML models, 336x faster than Python” “I have been waiting for this!”
Comment from 2 Mar 2026 in “Show HN: Timber – Ollama for classical ML models, 336x faster than Python” Skips Python and shared libraries
“This lets you not even need Python, r, Julia, etc but directly connect to your backend systems”
Comment from 2 Mar 2026 in “Show HN: Timber – Ollama for classical ML models, 336x faster than Python” “this approach is much simpler and portable than shared libraries across platforms”
Comment from 2 Mar 2026 in “Show HN: Timber – Ollama for classical ML models, 336x faster than Python”
What people warn about
Each mark is one comment
Inference speedup adds little overall
“optimizing the inference time has marginal benefit in the overall pipeline”
Comment from 2 Mar 2026 in “Show HN: Timber – Ollama for classical ML models, 336x faster than Python” Unclear value for full-pipeline owners
“if you own the entire training to inference pipeline i'm not sure what this offers?”
Comment from 2 Mar 2026 in “Show HN: Timber – Ollama for classical ML models, 336x faster than Python” Wants raw input instead of features
“Wouldn't it be much more useful if the request received raw input (i.e. before feature extraction), and not the feature vector?”
Comment from 2 Mar 2026 in “Show HN: Timber – Ollama for classical ML models, 336x faster than Python”
Other inference engines people recommend
The four most recommended other inference engines, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| vLLM | 112 | 56 | 67% | 12 | — | Approved |
| Strata | 31 | 15 | 67% | 5 | — | Approved |
| DwarfStar 4 | 26 | 2 | 93% | 6 | — | Approved |
| SGLang | 19 | 13 | 59% | 8 | — | — |
| TimberThis page | 9 | 2 | 82% | 3 | — | — |
What people said
All 11 comments that mention it, newest first. Each links to the original comment.
“Anything you can read can be read to you in hundreds of free voices”
“336x faster than Python, and swapping backends in a production environment can be far from trivial”
“Wouldn't it be much more useful if the request received raw input (i.e. before feature extraction), and not the feature vector?”
“Nice idea, i needed something like it”
“This lets you not even need Python, r, Julia, etc but directly connect to your backend systems”
“optimizing the inference time has marginal benefit in the overall pipeline”
“this approach is much simpler and portable than shared libraries across platforms”
“if you own the entire training to inference pipeline i'm not sure what this offers?”
“the concept alone sounds great”
“I have been waiting for this!”
“it's been amazing to watch you guys succeed”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.