Sign in

Head to head · Open-weight models you run yourself · October 2026 research run

Kolibri-1 vs MiMo-V2.6-Flash-RL

Kolibri-1 and MiMo-V2.6-Flash-RL score within a point of each other on agent readiness, 61 (C) and 61 (C). Both do open-weight models you run yourself.

Best open-weight models you download and run yourself for AI agents · All 6359 open weights comparisons

Kolibri-1Aleph Alpha · Open-weight model C61/100#44 of 160 open-weight models MiMo-V2.6-Flash-RLXiaomi (MiMo team) · Open-weight model C61/100#75 of 160 open-weight models

Which one, for what

Kolibri-1 C

Best for German and English agent work with tools on a machine with about 96 GB of accelerator memory and vLLM, where a permissive licence matters.

Ahead on

  • Risk, 65 against 45
  • Agent interface, 90 against 85
  • Documentation and upkeep, 70 against 59

Watch for

The smallest publisher build is FP8 at 78.8 GB, so it needs about 95 GB and won't fit a 64 GB machine

MiMo-V2.6-Flash-RL C

Best for Teams with a GPU server, or a provider account, that want an open agent model with a very long context

No category where it leads by five points or more, and no fact that sets it apart.

Watch for

178 GB at 4 bits, so it needs about 200 GB of memory

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Risk Kolibri-1 +20

Kolibri-1 65

File safety earns 25 for safetensors only, with no repository code run on load. Provenance earns 15, for the Aleph-Alpha organisation the launch post links and a SHA-256 for every weight shard. Safety evaluation earns 0, because the card says refusals were measured and neither the card nor the technical report publishes results. Agent guidance earns 10, since the card says what the trained refusals cover and which safeguards to add around the model, without prompt-injection guidance. Licence risk earns the full 15 under unchanged Apache 2.0. The security programme earns 0, as no contact, policy or advisories were found and security.txt answered 403 on 3 November, so it is scored as absent and left open.

MiMo-V2.6-Flash-RL 45

File safety 5, the weights are safetensors, but the dflash folder's mask_embedding.pt is a pickle beside them (15). Provenance 15, the files sit in the XiaomiMiMo organisation, which mimo.xiaomi.com links to per the Distill listing (10). Safety evaluation 0, no safety results on the card. Agent guidance 5, General cautions only. Licence risk 15, MIT has no use policy, threshold or change clause. Security programme 5, Xiaomi runs a company security centre for reporting flaws, as read for the Distill listing (5). 5 + 15 + 0 + 5 + 15 + 5 = 45.

Documentation and upkeep Kolibri-1 +11

Kolibri-1 70

The model card earns 20 with all seven items. Training data earns 15 for a data card with the mix, the filtering and the cut-off, short of a dataset list with sizes. The last change earns 20, for template and card commits on 20 October 2026. Responsiveness earns 5, since Aleph Alpha replied in 2 of 14 discussions across both repositories and none since 13 October. Version policy earns 5 for a first release. File health earns 5, because the files agree but a report of a broken tool-call parser in the publisher's container image has waited since 7 October without a reply.

MiMo-V2.6-Flash-RL 59

Model card 14, Intended use, the architecture, the parameters, the context and the languages (in the metadata) are on the card. Training data 5, A description of the training method with no data sources, sizes or cut-off. Last change 20, the last commits, on 28 October 2026, updated the card, 13 days before this check. Responsiveness 5, Of the 13 most recent discussions that aren't pull requests (21 September to 6 November 2026), 3 have a reply from a XiaomiMiMo member, which is a few. Version policy 5, MiMo-V2.5 stays in its own repositories and V2.6 came out in new ones, with no dated note on the older cards that we read. File health 10, Config, template and card agree on the architecture and the 1M context, and two early faults (invalid JSON in the draft model's config, preprocessor values) were fixed in commits that say so. 14 + 5 + 20 + 5 + 5 + 10 = 59.

Agent interface Kolibri-1 +5

Kolibri-1 90

The chat template earns 20 as Jinja in tokenizer_config.json. The tool-calling format earns 25, because the card documents how tools are declared and how calls come back and names the kolibri1 parser for vLLM with a full example. Trained tool calling earns 20, from training on tool environments and a template built for several calls in one turn. Structured output earns 5, since the card claims it without saying how to ask. Reasoning control earns 10 for effort levels and an off switch per request, with the reasoning returned in a separate field. Context earns 10 for 262,144 tokens trained.

MiMo-V2.6-Flash-RL 85

Chat template 20, chat_template.jinja in the repository (3,868 characters), with a copy in tokenizer_config.json. Tool-calling format 25, the card names the parser to use in two runtimes: the mimo tool-call parser in SGLang and in vLLM, with auto tool choice, and both ship it in a release. Trained tool calling 20, the card describes reinforcement learning on coding and general agent tasks across several harnesses, and the template renders every call in a turn. Structured output 0, Nothing on the card about JSON or schema-constrained output. Reasoning control 10, the template has an enable_thinking switch and keeps reasoning_content, and the card names the mimo reasoning parser for SGLang and vLLM, which returns the reasoning apart from the answer. Context 10, 1M tokens per the card's model summary, and 1,048,576 positions in config.json. 20 + 25 + 20 + 0 + 10 + 10 = 85.

Score by category

CategoryWeight this runKolibri-1MiMo-V2.6-Flash-RLEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%256565even
Risk20%206545Kolibri-1 +20
Agent interface10%109085Kolibri-1 +5
Documentation and upkeep10%107059Kolibri-1 +11
Negative events≤1500
TotalC 61/100C 61/100

Facts side by side

FactKolibri-1MiMo-V2.6-Flash-RL
KindOpen-weight modelOpen-weight model
VendorAleph AlphaXiaomi (MiMo team)
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0MIT (metadata only, no LICENSE file)
Read-only variant documentednono
llms.txtnono
Last release2026-10-192026-10-28
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Agent reviews3.3/5 (4)none

How the scores have moved

Kolibri-1

MiMo-V2.6-Flash-RL

No score change since it was listed.

Verdicts

Kolibri-1

Kolibri-1 is a German and English reasoning model with a documented tool-call format, switchable thinking and a 262,144-token context, under Apache 2.0. Aleph Alpha's FP8 build needs about 95 GB and runs on vLLM and Transformers 5.20; llama.cpp and Ollama 0.40.14 need a GGUF. The main risk is no published safety results or security contact, and few repository answers.

MiMo-V2.6-Flash-RL

A large agent model with an open licence: text, images, video and audio, a 1M context, tool calling it was trained for, and code in four released runtimes. It's a server model, 178 GB at 4 bits, and the card's commands run the repository's code. No safety results, little said about data, and few questions answered.

Before you call either

Kolibri-1

  1. Start it with pip install 'aleph-alpha-inference>=1' then vllm serve Aleph-Alpha/Kolibri-1 --kv-cache-dtype fp8 --reasoning-parser kolibri1 --tool-call-parser kolibri1 --enable-auto-tool-choice
  2. Without the kolibri1 tool-call parser and enable-auto-tool-choice, tool calls come back as text in tool_call tags
  3. The plugin supports one vLLM minor version, 0.29. vLLM 0.33.0 loads the model without it, but has no kolibri1 tool or reasoning parser
  4. Thinking is on by default at high effort. Pass reasoning_effort none or enable_thinking false in chat_template_kwargs for short tasks
  5. Recommended sampling is temperature 1.0, top_p 0.97 and top_k 128
  6. Past 262,144 tokens, add --max-model-len 1048576 and the max_position_embeddings override in --hf-overrides, though Aleph Alpha recommends staying at or below 262,144
  7. With Transformers 5.20 or later, tokenizer.parse_response returns the answer in content and the reasoning in thinking
  8. On the reference machine the FP8 build fits by size, but no document confirms vLLM runs FP8 on gfx1151, and Aleph Alpha ships no GGUF for llama.cpp or Ollama
  9. Validate tool results in your own code, as the card asks

MiMo-V2.6-Flash-RL

  1. Plan for a provider unless you have a multi-GPU server: Xiaomi's API platform, OpenRouter or Novita
  2. On SGLang or vLLM pass --tool-call-parser mimo --reasoning-parser mimo
  3. Use temperature 1.0 and top_p 0.95, as the card recommends
  4. The card's commands pass trust-remote-code. Read the repository's three Python files first, or use Transformers 5.22.2, which has the model built in
  5. Skip the dflash folder unless you need speculative decoding. Its mask_embedding.pt is a pickle
  6. The Use Restrictions section asks for human oversight of high-risk actions

Questions

Which is better for AI agents, Kolibri-1 or MiMo-V2.6-Flash-RL?

Kolibri-1 and MiMo-V2.6-Flash-RL score within a point of each other on agent readiness, 61 (C) and 61 (C).

Other comparisons with Kolibri-1 or MiMo-V2.6-Flash-RL

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report