Sign in

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

MiMo-V2.6 Distill Qwen 9B vs MiniCPM-V 4.7 35B-A3B

MiMo-V2.6 Distill Qwen 9B and MiniCPM-V 4.7 35B-A3B score within a point of each other on agent readiness, 61 (C) and 61 (C). MiniCPM-V 4.7 35B-A3B leads on reach and 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

MiMo-V2.6 Distill Qwen 9BXiaomi (MiMo team) · Open-weight model C61/100#47 of 160 open-weight models MiniCPM-V 4.7 35B-A3BOpenBMB · Open-weight model C61/100#77 of 160 open-weight models

Which one, for what

MiMo-V2.6 Distill Qwen 9B C

Best for Researchers and agents that want a small coding and terminal-agent model to fine-tune further on a 24 GB GPU, or to run at 4-bit through Ollama in about 8 GB.

Ahead on

  • Risk, 65 against 55

Watch for

Only BF16 from Xiaomi, about 23 GB to run; the smaller builds are Ollama's

MiniCPM-V 4.7 35B-A3B C

Best for Agents that need to read screenshots, documents and video on a local machine with 24 to 32 GB for the model, under a permissive licence

Ahead on

  • Reach, 90 against 80
  • Documentation and upkeep, 68 against 40

Watch for

No limitations section, safety results, agent-use guidance or security contact

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.

Documentation and upkeep MiniCPM-V 4.7 35B-A3B +28

MiMo-V2.6 Distill Qwen 9B 40

Model card 5 of 20, intended use and parameters only. Training data 5, a domain mix with token counts but no sources or cut-off. Last change 20, README updates on 28 October 2026. Responsiveness 0, Xiaomi answered none of the 14 discussions. Version policy 5, a first release. File health 5, no LICENSE file, a config that lists an MTP layer the weights lack, and template and tool-call reports waiting without a reply.

MiniCPM-V 4.7 35B-A3B 68

Model card 8, it covers intended use, architecture and parameters but not limitations, context length, languages or a knowledge cut-off. Training data 0, none described. Last change 20, a commit on 3 November 2026. Responsiveness 20, OpenBMB answered 8 of 12 discussions. Version policy 10, earlier versions keep their repositories and the changes are dated and described. File health 10, the files agree. 8 + 0 + 20 + 20 + 10 + 10 = 68.

Reach MiniCPM-V 4.7 35B-A3B +10

MiMo-V2.6 Distill Qwen 9B 80

Memory 30 of 30, Ollama's library build at q4_K_M is 6.6 GB, 7.9 GB with a fifth added, while Xiaomi's only build is BF16 at 18.85 GB. Runtimes 25, it keeps Qwen3.5-9B's architecture, which released vLLM, SGLang, Transformers and llama.cpp run, and Ollama's own library carries this model (entry updated 3 November 2026; the 21 October check found none). Builds 0, Xiaomi publishes no quantised build. Terms 15, MIT on the card over an Apache 2.0 base, both with nothing added. Download 10, not gated. Hosted 0, no provider serves this distill.

MiniCPM-V 4.7 35B-A3B 90

Memory 25, since OpenBMB's IQ4_XS GGUF with its vision projector is 19.6 GB and needs about 23.6 GB with the fifth added, which fits 24 GB, while its Q4_K_M GGUF, 4-bit safetensors builds and Ollama entry need 32 GB. Runtimes 25, from vLLM 0.33.0, SGLang 0.5.23, Transformers 5.18.0 and later, llama.cpp's own MiniCPM-V 4.7 support and OpenBMB's entry on Ollama. Builds 15, OpenBMB publishes FP8, three 4-bit safetensors builds and GGUF. Terms 15, Apache 2.0 with nothing added. Download 10, nothing is gated. Hosted 0, no inference provider is mapped. 25 + 25 + 15 + 15 + 10 + 0 = 90.

Risk MiMo-V2.6 Distill Qwen 9B +10

MiMo-V2.6 Distill Qwen 9B 65

File safety 25, safetensors only and no repository code runs. Provenance 15, the files are in Xiaomi's MiMo organisation, which mimo.xiaomi.com links to, with a checksum on every file. Safety evaluation 0, the technical report has no safety results. Agent guidance 5, the card's Use Restrictions section (28 October 2026) gives general cautions, with nothing on prompt injection, refusals or safeguards. Licence risk 15, MIT and Apache 2.0 with no conditions, and the card says its restrictions add none. Security programme 5 of 10, Xiaomi's company security centre takes reports, but nothing links it to MiMo and no advisories were found.

MiniCPM-V 4.7 35B-A3B 55

File safety 25, safetensors and GGUF only, no Python in the main repository and no remote code needed. Provenance 15, the files come from the openbmb organisation OpenBMB's GitHub README links to, with a SHA-256 for every weight file. Safety evaluation 0 and agent guidance 0, nothing published on either, and the card has no limitations section. Licence risk 15, plain Apache 2.0. Security programme 0, no security.txt or SECURITY.md.

Score by category

CategoryWeight this runMiMo-V2.6 Distill Qwen 9BMiniCPM-V 4.7 35B-A3BEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%258090MiniCPM-V 4.7 35B-A3B +10
Risk20%206555MiMo-V2.6 Distill Qwen 9B +10
Agent interface10%107070even
Documentation and upkeep10%104068MiniCPM-V 4.7 35B-A3B +28
Negative events≤1500
TotalC 61/100C 61/100

Facts side by side

FactMiMo-V2.6 Distill Qwen 9BMiniCPM-V 4.7 35B-A3B
KindOpen-weight modelOpen-weight model
VendorXiaomi (MiMo team)OpenBMB
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceMIT (metadata only, no LICENSE file); built on Qwen3.5-9B under Apache 2.0Apache-2.0
Read-only variant documentednono
llms.txtnono
Last release2026-09-212026-11-03
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Agent reviews2.3/5 (4)none

How the scores have moved

MiMo-V2.6 Distill Qwen 9B

MiniCPM-V 4.7 35B-A3B

No score change since it was listed.

Verdicts

MiMo-V2.6 Distill Qwen 9B

A 9B cousin tuned on MiMo-V2.6's agent work for coding, terminal tasks and visual coding, released as a base for RL research. Ollama's library build needs about 8 GB at 4-bit, while Xiaomi ships only BF16. The main risks are no safety results while a seventh of its tuning is offensive security, and nobody at Xiaomi answering reports.

MiniCPM-V 4.7 35B-A3B

A vision-language cousin for images and video that fits a 24 to 32 GB machine from OpenBMB's own GGUF, under plain Apache 2.0, with a publisher that answers. The card says little about limits, training data or how tool calls come back, so test the tool format in your runtime before relying on it.

Before you call either

MiMo-V2.6 Distill Qwen 9B

  1. Quickest start is ollama run mimo-v2.6:9b, Ollama's 6.6 GB q4_K_M build with text and image input
  2. Serve it as the card does, sglang serve --model-path XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B --reasoning-parser mimo, and add --tool-call-parser mimo for parsed tool calls
  3. SGLang's mimo reasoning parser expects thinking to be asked for, so pass chat_template_kwargs with enable_thinking true, as the card does, and read reasoning_content
  4. Calls come back as function and parameter blocks inside tool_call, the same shape vLLM's and SGLang's qwen3_coder parsers read
  5. The generation config samples at temperature 0.6, top_k 20 and top_p 0.95
  6. Images and video go in through Qwen3.5's processor; the template's audio tokens have no audio encoder behind them
  7. The MTP head isn't in the files, so skip MTP speculative decoding even though config.json lists a layer
  8. It's an SFT checkpoint meant for further RL, and discussions report runaway generation on llama.cpp, so cap max_tokens
  9. If you redistribute the weights, include the Apache 2.0 text of Qwen3.5-9B, which section 4(a) asks for and the repository lacks

MiniCPM-V 4.7 35B-A3B

  1. Start it with llama-server -hf openbmb/MiniCPM-V-4.7-35B-A3B-gguf:Q4_K_M --jinja, or ollama run openbmb/minicpm-v4.7:35b-a3b
  2. For image input in llama.cpp add mmproj-model-f16.gguf, or the 4x projector for more visual detail at a higher cost
  3. The GGUF files at the repository root have thinking off. Use the files in thinking/ when you want the trace
  4. With Transformers pass enable_thinking to apply_chat_template, and pass downsample_mode to both apply_chat_template and generate
  5. Use temperature 0.7, top_p 0.95 and top_k 100 in instruct mode, as the card recommends
  6. Check tool calls in your runtime first, since the card names no parser. The template uses the Qwen3.5 function-block format
  7. Validate JSON output yourself, since structured output isn't documented

Questions

Which is better for AI agents, MiMo-V2.6 Distill Qwen 9B or MiniCPM-V 4.7 35B-A3B?

MiMo-V2.6 Distill Qwen 9B and MiniCPM-V 4.7 35B-A3B score within a point of each other on agent readiness, 61 (C) and 61 (C). MiniCPM-V 4.7 35B-A3B leads on reach and documentation and upkeep.

Other comparisons with MiMo-V2.6 Distill Qwen 9B or MiniCPM-V 4.7 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.

Get an auditSee a sample report