Ring-2.6 1T
Ring-2.6-1T is a reasoning model with adjustable effort settings: high is intended for agent workflows, while xhigh targets difficult reasoning tasks. Summary written by AI Index from Ant Group’s own pages.
- Out Output modalities: Text
- Reasoning· high, xhigh
- Tool use
- Open weights
Prices
1 offering · prices as listedRing-2.6-1T| Conditions/ 1M tokens | Input | Cache read | Output |
|---|---|---|---|
| Standard no longer listed since Oct 20, 2026 | ¥4.50 | ¥0.90 | ¥18.00 |
Prices from Ant Ling: model pricing (opens in a new tab) (checked Oct 19, 2026)
Standard: the price a request with no conditions pays (the headline price elsewhere on the site).
Details
- Licence
- MIT
- Family
- ring
- Model ID
Not stated on Ant Group’s pages: max input, input modalities, reasoning can be off, max thinking budget, structured output, built-in tools, knowledge cutoff, aliases.
Run locally
Weights: inclusionAI/Ring-2.6-1T- Parameters 1.03T
- Active 76.8B (estimated) · 256 experts, 8 per token
- Native precision BF16
- Layers 80
- KV cache per token 90 KB
- Config positions 128K (config.json max_position_embeddings)
- API context 250K (maker’s API)
- Needs
- ≈ 533.4 GB (weights 507.3 + KV cache 0.7 + overhead 25.4)
- Usable
- 21.6 GB (90% of its memory)
- Try
- it’s too large for this hardware; see the smallest that runs it below
| Precision | Weights | Needs at 8K | On your hardware | Longest context |
|---|---|---|---|---|
| BF16 (native)maker’s file | 970.3 GB | ≈ 1019.5 | ✕Doesn’t fit | — |
| Q8_0 | 1014.7 GB | ≈ 1066.1 | ✕Doesn’t fit | — |
| FP8 | 955.0 GB | ≈ 1003.4 | ✕Doesn’t fit | — |
| Q6_K | 784.3 GB | ≈ 824.2 | ✕Doesn’t fit | — |
| Q5_K_M | 679.2 GB | ≈ 713.9 | ✕Doesn’t fit | — |
| Q5_0 | 656.6 GB | ≈ 690.1 | ✕Doesn’t fit | — |
| Q4_K_M | 580.2 GB | ≈ 609.9 | ✕Doesn’t fit | — |
| Q4_0 | 537.2 GB | ≈ 564.7 | ✕Doesn’t fit | — |
| IQ4_XS | 507.3 GB | ≈ 533.4 | ✕Doesn’t fit | — |
| Q3_K_Mquality drops | 466.8 GB | ≈ 490.8 | ✕Doesn’t fit | — |
| IQ3_XXSquality drops | 365.3 GB | ≈ 384.3 | ✕Doesn’t fit | — |
| Q2_Kquality drops | 358.1 GB | ≈ 376.7 | ✕Doesn’t fit | — |
| IQ2_XXSquality drops | 245.9 GB | ≈ 258.9 | ✕Doesn’t fit | — |
Click a row to choose a precision. “Maker’s file” sizes are the maker’s own files; others are parameters × bits per weight.
Compared with other hardware
Each at the highest precision it runs. Click one for details.
Smallest that runs it (Q4_K_M, 8K): no single listed machine; about 9 × 80 GB GPUs.
Run commands
The maker publishes no files at this precision. Choose its native precision or one of its own builds, or quantise it yourself with llama.cpp.
Memory to fine-tune
Batch 1, 2,048-token sequences, gradient checkpointing; LoRA and QLoRA train rank-16 adapters on the attention projections.
Estimates; facts from the maker’s Hugging Face repositories, as of 2026-11-21. How it’s estimated
Cited scores
From third-party leaderboards, not measured by usThis model isn’t on any leaderboard we cite yet.
Changes
All changes →No changes recorded yet.
Sources
- Ant Ling: model pricing (opens in a new tab) developer.ant-ling.com · checked Oct 19, 2026
- Ant Ling: FAQ (opens in a new tab) developer.ant-ling.com · checked Oct 19, 2026
- Ant Ling: Ring models (opens in a new tab) developer.ant-ling.com · checked Oct 19, 2026
- Changelog (opens in a new tab) developer.ant-ling.com · checked Nov 8, 2026
- inclusionAI/Ring-2.6-1T model card (opens in a new tab) huggingface.co · checked Nov 8, 2026
- inclusionAI/Ring-2.6-1T model card (opens in a new tab) huggingface.co · checked Nov 8, 2026
- inclusionAI/Ring-2.6-1T model card (opens in a new tab) huggingface.co · checked Nov 6, 2026
- inclusionAI/Ring-2.6-1T files (opens in a new tab) huggingface.co · checked Nov 5, 2026
- inclusionAI/Ring-2.6-1T config.json (opens in a new tab) huggingface.co · checked Nov 4, 2026
Some values on this page are still waiting to be checked against official pages: a filled dot is verified, a hollow one is not yet (with or without a source on file). How we verify data
Ant Group · China · developer.ant-ling.com
Related models
Snapshots, the same family and other models from this provider