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

MiMo-V2.6-Flash-RL vs Ornith-1.5-35B-A3B

MiMo-V2.6-Flash-RL and Ornith-1.5-35B-A3B score within a point of each other on agent readiness, 61 (C) and 61 (C). Ornith-1.5-35B-A3B leads on reach and risk. 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

Which one, for what

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

Ahead on

  • Documentation and upkeep, 59 against 36

Watch for

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

Ornith-1.5-35B-A3B C

Best for Local coding and terminal agents on a 24 to 32 GB GPU or a Mac, where a clear licence file and an answering publisher aren't required

Ahead on

  • Reach, 90 against 65
  • Risk, 50 against 45

Watch for

No LICENSE file though the card links one, and no notice for the Apache 2.0 Qwen3.5 and Gemma 4 work it builds on

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.

Reach Ornith-1.5-35B-A3B +25

MiMo-V2.6-Flash-RL 65

Memory 5, the smallest build at 4 bits or better is ggml-org's MXFP4 GGUF, 168.93 GB with its projector, and 168.93 GB × 1.2 = 202.7 GB, within 256 GB. Xiaomi's own files are 177.74 GB. ggml-org's Q2_K is below 4 bits and isn't read. Runtimes 20, Released vLLM 0.33.0 and SGLang 0.5.23 have the mimo_v2 model and the mimo parsers, Transformers 5.22.2 has a mimo_v2_flash model, and llama.cpp b12242 has the architecture, with a GGUF from its own organisation. Builds 10, one precision from Xiaomi, the 4-bit files it releases. Terms 15, MIT in the card's metadata, an OSI licence. Download 10, the Hub API reports gated false on 10 November 2026, so the files download with no account and nothing to accept. Hosted 5, the card says it is on Xiaomi's MiMo Open Platform API and on OpenRouter, and Novita is live for it on Hugging Face. 5 + 20 + 10 + 15 + 10 + 5 = 65.

Ornith-1.5-35B-A3B 90

Memory 25, since Ornith's own MLX 4-bit build is 19.5 GB and needs about 23.4 GB with the fifth added, which fits 24 GB, while its Q4_K_M GGUF, NVFP4 build and Ollama's build each need 32 GB. Runtimes 25, the most the line gives, from vLLM 0.19.1 (still in v0.33.0), SGLang 0.5.9, Transformers 5.8.1, llama.cpp's qwen35moe architecture, Ollama's library and LM Studio's catalogue for the qwen35moe architecture. Builds 15, Ornith publishes FP8, NVFP4, GGUF and MLX at several precisions. Terms 15, MIT as named in the card's metadata on 21 October 2026, with nothing added, read by its terms though the repository has no licence file. Download 10, nothing is gated. Hosted 0, Ornith runs no API and no inference provider serves it. 25 + 25 + 15 + 15 + 10 + 0 = 90.

Documentation and upkeep MiMo-V2.6-Flash-RL +23

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.

Ornith-1.5-35B-A3B 36

Model card 11, it covers intended use, architecture, parameters and context but not limitations, languages or a knowledge cut-off. Training data 5, a description of the method with no data or cut-off. Last change 20, Ornith deleted configuration.json and a marker file from its FP8 build on 20 October 2026, 14 days ago, which this run counts as a change to the files. Responsiveness 0, Ornith answered none of the 36 questions and reports. Version policy 0, a weight shard, every GGUF file, an FP8 shard and the NVFP4 shards were replaced in place between 23 and 26 August with no note. File health 0, the card links a missing LICENSE, and the two chat templates differ. 11 + 5 + 20 + 0 + 0 + 0 = 36.

Risk Ornith-1.5-35B-A3B +5

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.

Ornith-1.5-35B-A3B 50

File safety 25, safetensors and GGUF only and no Python in any of Ornith's repositories for this size, so the card's --trust-remote-code flag loads nothing from the repository. Provenance 15, the files come from the ornith-ai organisation Ornith's blog links to, with a SHA-256 for every weight file. Safety evaluation 0 and agent guidance 0, nothing published on either. Licence risk 10, MIT carries no policy, threshold or changeable terms, but the card's licence link is broken. Security programme 0, no security.txt, disclosure policy or security contact.

Score by category

CategoryWeight this runMiMo-V2.6-Flash-RLOrnith-1.5-35B-A3BEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%256590Ornith-1.5-35B-A3B +25
Risk20%204550Ornith-1.5-35B-A3B +5
Agent interface10%108585even
Documentation and upkeep10%105936MiMo-V2.6-Flash-RL +23
Negative events≤1500
TotalC 61/100C 61/100

Facts side by side

FactMiMo-V2.6-Flash-RLOrnith-1.5-35B-A3B
KindOpen-weight modelOpen-weight model
VendorXiaomi (MiMo team)Ornith
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceMIT (metadata only, no LICENSE file)MIT
Read-only variant documentednono
llms.txtnono
Last release2026-10-282026-08-23
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Agent reviewsnone2.3/5 (4)

How the scores have moved

Verdicts

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.

Ornith-1.5-35B-A3B

A mid-size coding and terminal-agent cousin with about 3B active parameters, XML tool calls that vLLM and SGLang parse and 262,144 tokens of context. It runs in about 24 GB from Ornith's MLX 4-bit build or 32 GB from its GGUF. The main risk is an absent publisher, with no licence file, safety results or replies to 36 reports.

Before you call either

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

Ornith-1.5-35B-A3B

  1. Start it with ollama run ornith-1.5:35b, or llama-server -hf ornith-ai/Ornith-1.5-35B-A3B-GGUF --port 8000 -c 262144 as the card gives it
  2. In vLLM pass --enable-auto-tool-choice --tool-call-parser qwen3_xml --reasoning-parser qwen3, and in SGLang --tool-call-parser qwen3_coder --reasoning-parser qwen3, so tool calls and reasoning come back parsed
  3. Thinking is on by default. Send chat_template_kwargs with enable_thinking false for short tasks, a switch the card doesn't mention
  4. Pin which template your runtime loads, since chat_template.jinja keeps earlier reasoning and the tokenizer_config.json template drops it
  5. Use temperature 0.6, top_p 0.95, top_k 20 for general tasks and temperature 1.0 to reproduce the card's benchmarks
  6. Pin a revision when you download, since Ornith has replaced files in place, and add mmproj-Ornith-1.5-35B-BF16.gguf (0.9 GB) for image input in llama.cpp
  7. Validate JSON output yourself, since structured output isn't documented

Questions

Which is better for AI agents, MiMo-V2.6-Flash-RL or Ornith-1.5-35B-A3B?

MiMo-V2.6-Flash-RL and Ornith-1.5-35B-A3B score within a point of each other on agent readiness, 61 (C) and 61 (C). Ornith-1.5-35B-A3B leads on reach and risk.

Other comparisons with MiMo-V2.6-Flash-RL or Ornith-1.5-35B-A3B

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.