Ember-1
Shares rank 44 of 72 language models by recommenders
Recommended for using far fewer tokens per task, which can cut cost in long conversations. Critics report hallucinations and higher pricing than its base model.
Recommended for using far fewer tokens per task, which can cut cost in long conversations. Critics report hallucinations and higher pricing than its base model.
15 people gave an opinion
- recommend it
- 11
- criticize it
- 4
- approval share
- 73%
Recommended in 1 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: not recommended
- March 2026: not recommended
- April 2026: not recommended
- May 2026: not recommended
- June 2026: not recommended
- July 2026: not recommended
- August 2026: not recommended
- September 2026: recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 11 people recommend itNeeds 10 or more, met.
- 2.8 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 1 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
Far fewer tokens per task
“Because you care about how many tokens are used per task.”
Comment from 27 Sep 2026 in “Ember-1” “Half the tokens can also mean quicker task completion”
Comment from 28 Sep 2026 in “Ember-1” “For long conversations, you end up paying much less.”
Comment from 28 Sep 2026 in “Ember-1” - Comment from 29 Sep 2026 in “Sonnet 5.5”
Praised as a great iteration
“Well done, and great iteration.”
Comment from 27 Sep 2026 in “Ember-1” “This is undoubtedly great.”
Comment from 27 Sep 2026 in “Ember-1”
What people warn about
Each mark is one comment
Higher cost per token than base
“Half the tokens, but triple the cost on Open Router? So I pay more?”
Comment from 28 Sep 2026 in “Ember-1” “But the pricing is double the pricing of K3.”
Comment from 27 Sep 2026 in “Ember-1” Hallucinates and claims false completion
“Their Ember-1 model (Kimi K3 tuned to think less) hallucinates to high hell, I have no trust of it”
Comment from 19 Oct 2026 in “MiniMax M3.1 Flash” “It hallucinated and claimed task completion almost every session.”
Comment from 23 Oct 2026 in “Gemma-4-26B-A4B with 39-69% less thinking at same accuracy” Poor past experience with Ember-2
“Given what an experience i had with Ember-2”
Comment from 27 Sep 2026 in “Ember-1” “Not what I signed up for though.”
Comment from 28 Sep 2026 in “Ember-1”
Other language models people recommend
The four most recommended other language models, 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 |
|---|---|---|---|---|---|---|
| Claude Opus | 3,331 | 2,746 | 55% | 13 | 4 mo156 owners | — |
| OpenAI GPT | 1,205 | 987 | 55% | 13 | 6 mo47 owners | — |
| Claude Sonnet | 854 | 586 | 59% | 13 | 6 mo46 owners | — |
| DeepSeek V4 Flash | 828 | 223 | 79% | 8 | 1 mo24 owners | Approved |
| Ember-1This page | 11 | 4 | 73% | 1 | — | — |
What people said
All 16 comments that mention it, newest first. Each links to the original comment.
“It hallucinated and claimed task completion almost every session.”
“Their Ember-1 model (Kimi K3 tuned to think less) hallucinates to high hell, I have no trust of it”
“the private, local, homegrown specialized English-to-bash translator”
“fine-tune of Kimi3 with way less thinking”
“Half the tokens can also mean quicker task completion”
“Half the tokens, but triple the cost on Open Router? So I pay more?”
“For long conversations, you end up paying much less.”
“Not what I signed up for though.”
“It's same price for lower latency.”
“Because you care about how many tokens are used per task.”
“But the pricing is double the pricing of K3.”
“This is undoubtedly great.”
“Given what an experience i had with Ember-2”
“jev can be great for running periodic evals especially those that run daily.”
“set a new Pareto frontier for Bedside Bench across both open and closed models”
“Well done, and great iteration.”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.