Mirendil Introduces Fern, a From-Scratch Model with 10M-Token Context
Mirendil announces Fern, its first model, pretrained from scratch with a context window of up to 10M tokens. The first version, Fern 0.1, was finished with a short round of post-training. The page describes Fern 0.1 as the company's most efficient model, built for focused, high-volume agentic tasks, with a base model called Mirendil-Base, a size of 0.1 to 0.5T parameters, and text and code input. Access is listed as coming soon, with an early access request option.
Open original source mirendil.comOne primary source; other links are context, not independent corroboration.
- Primary sourceX discovery · automated brief
- Discovery linkX
Grok Bot submitted the link. AINewsIQ fetched the primary source and prepared a source-based brief automatically. An editor has not reviewed the story; social attention and the brief do not independently verify its claims.
- Linked article+30
- Fetched source page+30
- No editor link review0
- Original non-discussion link+5
This measures the stored source trail and editorial steps. It does not certify accuracy, peer review, or independent corroboration. Popularity adds no points.
View full scoring →Read the scoring rubric →What the source says
Mirendil announces Fern, its first model, pretrained from scratch with a context window of up to 10M tokens. The first version, Fern 0.1, was finished with a short round of post-training. The page describes Fern 0.1 as the company's most efficient model, built for focused, high-volume agentic tasks, with a base model called Mirendil-Base, a size of 0.1 to 0.5T parameters, and text and code input. Access is listed as coming soon, with an early access request option.
A READER'S EVIDENCE CHECKHow to read this signalSix questions about claims, sources, risks, and open checks
This is a signal-level guide until claim-level evidence is available. “Not recorded” means the evidence has not been assessed here; it does not mean a result is false. How we check AI news →
- 01Who is making each claim?
The claimant and whether each claim was measured or asserted are not recorded in this public brief.
- 02What was actually tested?
Not recorded per claim. Check the source for sample size, tasks, model and benchmark versions, and reproducibility.
- 03Where are the sources?
Original link: mirendil.com. Brief basis: fetched source page. Primary page date and quote locations are not established in this panel.
- 04What could mislead?
Source claims not independently checked; the page gives no benchmarks, and access is listed only as coming soon.
- 05What is at risk if wrong?
Not assessed per claim. Consider safety, privacy, cost, and adoption decisions before relying on the result.
- 06What would change the view?
No claim-specific check is recorded. An inspectable primary method or independent replication could change the assessment.
Key findings from the stored brief
- Fern is Mirendil's first model and is pretrained from scratch.
- Fern supports a context window of up to 10M tokens.
- Fern 0.1 is described as the most efficient model, built for high-volume agentic tasks.
- Fern 0.1 lists a size of 0.1 to 0.5T parameters and accepts text and code input.
Source claims not independently checked; the page gives no benchmarks, and access is listed only as coming soon.
This is a source-based abstract, not independent validation of the source's claims.
Evidence & sources
These links show where the signal came from and what the source page linked to. A linked page is context, not independent corroboration.
These are Grok Bot discovery notes. AINewsIQ prepared a brief from available source material. The bot's rationale, linked posts, authors, and stances have not been independently verified.
Mirendil's Oct 26 post introduces Fern, pretrained from scratch with a context window of up to 10M tokens. Fern 0.1 is built on Mirendil-Base (0.1–0.5T params) for high-volume agentic tasks; access is 'coming soon' via an early-access request. Two larger base models are listed as still in pretraining. Long-context results are company-reported (RULER), with more promised.
Source claims not independently checked; the page gives no benchmarks, and access is listed only as coming soon.
Engagement counts, when shown, are observed snapshots. They do not establish accuracy or corroboration.
- x post ↗ · 628 likes, 57 reposts, 21 replies, 37 quotes · observed 10/27/2026, 4:01:48 AM
- Related post ↗
- Related post ↗
Related archive coverage
These relationships record a citation or topic overlap, not confirmation of the finding.
Grok Bot submitted the link. AINewsIQ fetched the primary source and prepared a source-based brief automatically. An editor has not reviewed the story; social attention and the brief do not independently verify its claims.
Timeline & updates
- Signal dated by source or discovery feed
This timestamp places the signal in the radar. It may be the discovery post date rather than the primary page's first publication date.
- Shared brief stored
AINewsIQ prepared one abstract from fetched source page.
A publication revision history is not stored for this signal. New engagement snapshots do not mean the source itself changed.
Why this may matter
A from-scratch model with a very large context window and an explicit focus on agentic workloads could matter for developers building long-context, high-throughput applications, if the stated capabilities hold up in practice.
Limits and open questions
Source claims not independently checked; the page gives no benchmarks, and access is listed only as coming soon.
Organization-specific financial, security, and operational effects require the organization's own context and review.
Discussion
Comments are reviewed before publication. Discuss the evidence, not the person.
No published comments yet.
Reader discussion opens with accounts. You can read the original source and published comments now.