Up to date
XiaomiMiMo MIT out 18 months ago
7.83B parameters, text in, text out, 32K tokens of context.
Verified 2026-10-25 Rank #698 in LLMs · score 72.1 method v1 Sources 3 Downloads 30d 31k · #421 of 619 tracked
Picked by rule from 11 tracked pieces: the lab's own post, the most shared, a field report, the latest.
MiMo-V2.6-Pro is a multimodal open-weight model from Xiaomi released on September 21, 2026, that scores 46 on the Artificial Analysis Intelligence Index.
The 2 picks above, plus these 9. Top is the radar's score: discussion, source authority and the lab's own posts, fading with age.
Hugging Face does not say who downloads a model or with what. These are the proxies: API providers listing it, quantized builds, fine-tunes/adapters/merges, and Spaces that load it.
No API provider serves it, so its downloads are people running it themselves: 3 quantized builds and 8 Spaces.
Top Spaces running it: ISEEKYAN/megatron_memory_estimator ♥ 35 · ISEEKYAN/megatron_memory_estimator_old ♥ 19 · orangewong/xiaomi-mimo-7b-rl ♥ 8
Weights only, an estimate: leave room for the KV cache. Method
About 4.7 GB at INT4, 9.4 GB at FP8, 19 GB at BF16: weights only, so leave room for the KV cache.
Estimate params × bytes per param × 1.2 · how we estimate
Weights, every dated article, and repo commits on one rail.
Teal is the weights (2025-04-29), amber triangles are 10 dated articles (each links to it), grey ticks are repo commits.
3 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.
From the Hugging Face model tree; quantized builds in teal, fine-tunes, merges and adapters in greys.
Everything else, folded: the full tables, every source.
Labels are evidence, not verdicts: measured a third-party leaderboard row for this model; author-reported a number the model author published in the card or eval files; structural a deterministic signal from the name, config or chat template, or a decision-model estimate. Each chip links to its source. All use cases.
Listed in LLMs
| Pipeline tag | text-generation |
|---|---|
| Library | transformers |
| Architectures | MiMoForCausalLM |
| Model type | mimo |
| Dtype | bfloat16 |
| Params by dtype | BF16: 7,833,409,536 |
| Size band | M |
| MoE | no |
| Context length | 32,768 (config.json max_position_embeddings) |
| Papers | arXiv:2505.07608 |
| License | MIT (mit) |
| Hub snapshot | 2026-10-25 |
vLLM: supported · MiMoForCausalLM · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · MiMoForCausalLM · 773cb938fe9484a8f7e7e46fb1b1fe96412c59ed
vLLM registry (7050ef881ff0835f6890a47db1859a24c65481d6) · SGLang registry (773cb938fe9484a8f7e7e46fb1b1fe96412c59ed) · Matched by architecture class name against each project's registry on main; 'supported' means the architecture is registered, not that this checkpoint was tested.
Weights-only memory for MiMo-7B-RL: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 19 GB · Single GPU (<24 GB) |
|---|---|
| FP8 (1 byte/param) | 9.4 GB · Single GPU (<24 GB) |
| INT4 (0.5 bytes/param) | 4.7 GB · Single GPU (<24 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.
quantized: 3
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| jedisct1/MiMo-7B-RL-GGUF | quantized | GGUF | — | — | mit | jedisct1 | 30 | 43.4k |
| quantflex/MiMo-7B-RL-nomtp-GGUF | quantized | GGUF | — | — | mit | quantflex | 2 | 6.6k |
| mlx-community/MiMo-7B-RL-4bit | quantized | -4bit | 7.62B | M | mit | mlx-community | 1 | 1.5k |
| Date | Commit | SHA |
|---|---|---|
| 2025-06-05 | Update README.md | 6299b5a |
| 2025-05-13 | Update README.md | 8aa36ea |
| 2025-05-13 | [Add] `tokenizer_class` in config to make it usable by the `pipeline` API (#10) | 5304ef1 |
| 2025-05-05 | Add library_name to the model (#2) | 5d40cdb |
| 2025-05-05 | Update README.md | 9c071e0 |
| 2025-04-30 | Update formulas in README.md | 8c8a496 |
| 2025-04-30 | init Xiaomi-MiMo | 163b6d7 |
| 2025-04-30 | init Xiaomi-MiMo | 68c4525 |
| 2025-04-29 | init Xiaomi-MiMo | 6103a58 |
| 2025-04-29 | initial commit | 54501ee |
Ranked by source signals (HN, Lobsters, authority domains, official posts) and recency. Summaries are generated from a stored copy of the article text; every sentence cites a span of that text, and nothing is shown that failed the citation check.
arXiv links found in the model card and its tags. "Peer-reviewed" is shown only with evidence: a published venue in OpenAlex (measured) or the authors' own journal reference on arXiv (reported).
Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:41 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:46 UTC · Summary: 2026-10-07 15:13 UTC · Last verified 2026-10-25
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.
