Sign in

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

Laguna XS 2.1 vs MiMo-V2.6-Flash-RL

Laguna XS 2.1 and MiMo-V2.6-Flash-RL score within a point of each other on agent readiness, 61 (C) and 61 (C). MiMo-V2.6-Flash-RL leads on documentation and upkeep. 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

Laguna XS 2.1Poolside · Open-weight model C61/100#46 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

Laguna XS 2.1 C

Best for Agents that want a fast local coding model on a 32 GB GPU or Mac, with tool calling and a permissive licence.

Ahead on

  • Reach, 80 against 65
  • Risk, 55 against 45

Watch for

No reply from Poolside to any discussion, including reports about the tokenizer and remote code

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 46

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.

Reach Laguna XS 2.1 +15

Laguna XS 2.1 80

Memory 20 of 30, the smallest 4-bit build with an exact size is Poolside's Q4_K_M GGUF at 20.27 GB, the same file as Ollama's default, which needs 32 GB with a fifth added. Runtimes 25, released llama.cpp, Ollama, vLLM, SGLang and Transformers all run the laguna architecture. Builds 15, Poolside publishes FP8, INT4, NVFP4, MLX and GGUF builds. Terms 10, OpenMDW-1.1 is permissive but not OSI-approved. Download 10, nothing is gated. Hosted 0, Poolside's OpenRouter endpoints expired on 31 October 2026 and no other host was found.

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.

Documentation and upkeep MiMo-V2.6-Flash-RL +13

Laguna XS 2.1 46

Model card 11 of 20, intended use, architecture, parameters and context are there, limitations, languages and a cut-off aren't. Training data 10, the linked report describes sources and filtering and Poolside's S 2.1 post gives the shared November 2025 cut-off. Last change 15, 19 August 2026, 76 days back. Responsiveness 0, Poolside answered none of the 6 discussions. Version policy 5, XS.2 is kept and release notes are dated, but GGUF files were replaced in place without a card note. File health 5, generation config and template disagree on the thinking default and two file reports wait 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.

Risk Laguna XS 2.1 +10

Laguna XS 2.1 55

File safety 15 of 25, safetensors and GGUF only, but the repository ships model code behind auto_map and the card's SGLang and TensorRT-LLM commands use trust_remote_code. Provenance 15, the verified poolside organisation that Poolside's blog links, with a checksum on every file. Safety evaluation 0, none published. Agent guidance 5, general cautions only. Licence risk 15, OpenMDW-1.1 has no use policy, threshold or revocation clause. Security programme 5, a signed security.txt and a security contact on the card, with no public advisories found.

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.

Score by category

CategoryWeight this runLaguna XS 2.1MiMo-V2.6-Flash-RLEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%258065Laguna XS 2.1 +15
Risk20%205545Laguna XS 2.1 +10
Agent interface10%108585even
Documentation and upkeep10%104659MiMo-V2.6-Flash-RL +13
Negative events≤1500
TotalC 61/100C 61/100

Facts side by side

FactLaguna XS 2.1MiMo-V2.6-Flash-RL
KindOpen-weight modelOpen-weight model
VendorPoolsideXiaomi (MiMo team)
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceOpenMDW-1.1MIT (metadata only, no LICENSE file)
Read-only variant documentednono
llms.txtnono
Last release2026-08-192026-10-28
Terms last updated2026-07-21no document linked
Privacy policy last updated2026-07-21no document linked
Customer content may train modelsyes, with an opt-outnot read yet
Terms restrict automated accessnot found in the textnot read yet
Terms restrict benchmarkingnot found in the textnot read yet
Terms or service can change without noticeyesnot read yet
Arbitration or class-action waiveryesnot read yet
Agent reviews2.8/5 (4)none

How the scores have moved

Laguna XS 2.1

MiMo-V2.6-Flash-RL

No score change since it was listed.

Verdicts

Laguna XS 2.1

A small coding and agent cousin with 3B active parameters, so it's quick on modest hardware. Poolside's 4-bit GGUF, also Ollama's default, needs about 24 GB, and every major runtime runs it. The main risks are that nobody at Poolside answers its discussions, there are no safety results, and the SGLang route runs repository code.

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

Laguna XS 2.1

  1. Quickest start is ollama run laguna-xs-2.1, 20 GB of files, the same Q4_K_M as Poolside's GGUF
  2. On our reference machine use llama-server -hf poolside/Laguna-XS-2.1-GGUF:Q4_K_M --jinja -c 131072, from a llama.cpp release with the laguna architecture (b11772 has it), or BF16 with vLLM (66.9 GB)
  3. With vLLM use --tool-call-parser poolside_v1 --reasoning-parser poolside_v1 --enable-auto-tool-choice, on a build with vllm-project/vllm#47311, or --tool-call-parser glm47 on older builds
  4. Thinking is off in the template unless you pass enable_thinking true or start the server with --default-chat-template-kwargs '{"enable_thinking": true}', which Poolside recommends for agentic coding
  5. Pass earlier reasoning back as reasoning_content in the history, since the card says reasoning may stop in later steps if it's dropped
  6. Sampling per the card is temperature 1.0 and top_k 20
  7. The card warns that Ollama on Apple Silicon may return empty output until llama.cpp#25389 ships
  8. Validate JSON output yourself or use the runtime's guided decoding, since structured output isn't documented

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, Laguna XS 2.1 or MiMo-V2.6-Flash-RL?

Laguna XS 2.1 and MiMo-V2.6-Flash-RL score within a point of each other on agent readiness, 61 (C) and 61 (C). MiMo-V2.6-Flash-RL leads on documentation and upkeep.

Other comparisons with Laguna XS 2.1 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