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

MiMo-V2.6 Distill Qwen 9B vs MiniCPM-V 4.7 1B

MiMo-V2.6 Distill Qwen 9B and MiniCPM-V 4.7 1B score within a point of each other on agent readiness, 61 (C) and 61 (C). MiniCPM-V 4.7 1B 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

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 1B C

Best for Agents that need a cheap local model to read screenshots, photos and short video on a phone, a laptop or beside a bigger model

Ahead on

  • Reach, 95 against 80
  • Documentation and upkeep, 48 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.

Reach MiniCPM-V 4.7 1B +15

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 1B 95

Memory 30, OpenBMB's own IQ4_XS GGUF is 0.64 GB, 1.54 GB with the 0.90 GB vision projector, and 1.54 GB × 1.2 = 1.9 GB, which fits 16 GB with room to spare. Runtimes 25, MiniCPMV4_7ForConditionalGeneration in vLLM's registry at v0.33.0, the minicpmv4_7 model type in SGLang's minicpmv.py at v0.5.23, the minicpmv4_7 model in Transformers at v5.22.2, a MiniCPM-V 4.7 guide and conversion code in llama.cpp at b12242, and an openbmb/minicpm-v4.7:1b tag in OpenBMB's namespace on Ollama, read as the 35B-A3B listing's is. Builds 15, OpenBMB publishes AWQ, GPTQ and int4 safetensors builds and a GGUF repository from IQ3_XS to F16, so quantised builds at two precisions or more. Terms 15, Apache 2.0 in the card's metadata and as the LICENSE of OpenBMB's MiniCPM-V repository, an OSI licence. Download 10, gated is false on the main repository and on the GGUF, AWQ, GPTQ and int4 repositories, so the files download with no account or terms. Hosted 0, Hugging Face lists no inference provider for the model (an empty provider mapping on 10 November 2026), and no provider's own list was read. 30 + 25 + 15 + 15 + 10 + 0 = 95.

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 1B 55

File safety 25, safetensors in the main repository and the AWQ, GPTQ and int4 builds, GGUF in the GGUF build, with no .bin, .pt, .pth or .py files in the main repository. Provenance 15, files in the openbmb organisation that OpenBMB's GitHub README links to (10), with a SHA-256 for both large files in the main repository (5). Safety evaluation 0, no safety results on the card. Agent guidance 0, the card has no limitations or disclaimer section, and no prompt-injection guidance, instruction hierarchy or statement of trained refusals. Licence risk 15, Apache 2.0 has no use policy, field-of-use limit, threshold or change clause, nothing is added on the card, and the LICENSE in OpenBMB's GitHub repository resolved on 10 November 2026. Security programme 0, no SECURITY.md in OpenBMB/MiniCPM-V and no security.txt on openbmb.cn (both 404 on 10 November 2026), and no advisories found. 25 + 15 + 0 + 0 + 15 + 0 = 55.

Documentation and upkeep MiniCPM-V 4.7 1B +8

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 1B 48

Model card 8, Intended use (image, multi-image and video understanding on device), architecture (early visual-token compression inside the vision encoder) and parameters (1B) are there. Training data 0, no description of the training data on the card. Last change 20, the last commit, on 30 October 2026, updated the card and removed an unused asset folder, eleven days before this check. Responsiveness 0, the repository has no discussions that aren't pull requests (two pull requests in all), so nobody has asked anything yet and the line reads as none answered, as settled in calibration. Version policy 10, MiniCPM-V 4.5 and 4.6 stay in their own repositories and the GitHub README dates each release. File health 10, Config, template and card agree on the architecture and the thinking switch, and no report waits without a reply, since there are no discussions. 8 + 0 + 20 + 0 + 10 + 10 = 48.

Score by category

CategoryWeight this runMiMo-V2.6 Distill Qwen 9BMiniCPM-V 4.7 1BEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%258095MiniCPM-V 4.7 1B +15
Risk20%206555MiMo-V2.6 Distill Qwen 9B +10
Agent interface10%107070even
Documentation and upkeep10%104048MiniCPM-V 4.7 1B +8
Negative events≤1500
TotalC 61/100C 61/100

Facts side by side

FactMiMo-V2.6 Distill Qwen 9BMiniCPM-V 4.7 1B
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 release2026-09-212026-10-30
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

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 1B

A vision-language cousin small enough for a phone, under plain Apache 2.0, that every runtime we count can load. The projector is bigger than the language model, so plan for about 2 GB. The card says nothing about limits or training data and doesn't show how a tool call comes back.

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 1B

  1. Start it with llama-server -hf openbmb/MiniCPM-V-4.7-1B-gguf:Q4_K_M --jinja, or ollama run openbmb/minicpm-v4.7:1b
  2. For image input in llama.cpp add mmproj-model-f16.gguf, or the smaller 4x projector
  3. The GGUF files at the repository root have thinking off. Use the files in thinking/ when you want the trace
  4. Use temperature 0.7, top_p 0.95 and top_k 100 in instruct mode, as the card recommends
  5. Check tool calls in your runtime first, since the card names no parser
  6. 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 1B?

MiMo-V2.6 Distill Qwen 9B and MiniCPM-V 4.7 1B score within a point of each other on agent readiness, 61 (C) and 61 (C). MiniCPM-V 4.7 1B leads on reach and documentation and upkeep.

Other comparisons with MiMo-V2.6 Distill Qwen 9B or MiniCPM-V 4.7 1B

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.