Sign in

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

MiniCPM-V 4.7 35B-A3B vs Qwen3.5-9B

MiniCPM-V 4.7 35B-A3B and Qwen3.5-9B score within a point of each other on agent readiness, 61 (C) and 60.5 (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

MiniCPM-V 4.7 35B-A3BOpenBMB · Open-weight model C61/100#77 of 160 open-weight models Qwen3.5-9BAlibaba (Qwen team) · Open-weight model C60.5/100#87 of 160 open-weight models

Which one, for what

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 85
  • Documentation and upkeep, 68 against 34

Watch for

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

Qwen3.5-9B C

Best for Agents that want a small multimodal tool-calling model on a laptop or a 16 GB GPU, under a plain licence

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

Watch for

No quantised build from Qwen itself

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 +34

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.

Qwen3.5-9B 34

Model card 14, it covers intended use, architecture, parameters, context and 201 languages but gives no limitations and no knowledge cut-off. Training data 5, a general line about trillions of multimodal tokens with no cut-off. Last change 5, the files and card last changed on 2 March 2026 (c202236), 247 days before 4 November, within a year. Responsiveness 0, no Qwen member replied in any of the 40 most recent of the 45 discussions that aren't pull requests (2 March to 29 September 2026). Version policy 5, a first release that was never replaced in place, with no dated notes across generations. File health 5, two reports about the files and card (15 and 51) are still open with no reply. 14 + 5 + 5 + 0 + 5 + 5 = 34. The card's highlights mention sparse Mixture-of-Experts for the series while this 9B is dense, but its own overview matches config.json, so it's not counted as a contradiction.

Reach MiniCPM-V 4.7 35B-A3B +5

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.

Qwen3.5-9B 85

Memory 30, Qwen publishes no quantised 9B, so the smallest 4-bit build from a runtime's own library is Ollama's qwen3.5:9b at 6.6 GB, about 7.9 GB with the fifth added, well under 16 GB. Runtimes 25, the cap, with vLLM listed in its stable docs, Transformers at released tags, llama.cpp, Ollama's library, LM Studio's own catalogue and SGLang all running the architecture. Builds 0, Qwen's FP8 and GPTQ repositories cover only the 27B and larger Qwen3.5 models, so every quantisation of the 9B is someone else's. Terms 15, plain Apache 2.0. Download 10, the repository isn't gated. Hosted 5, Together, Featherless AI, OVHcloud and DeepInfra are live for it on its Hugging Face page. 30 + 25 + 0 + 15 + 10 + 5 = 85.

Score by category

CategoryWeight this runMiniCPM-V 4.7 35B-A3BQwen3.5-9BEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%259085MiniCPM-V 4.7 35B-A3B +5
Risk20%205555even
Agent interface10%107070even
Documentation and upkeep10%106834MiniCPM-V 4.7 35B-A3B +34
Negative events≤1500
TotalC 61/100C 60.5/100

Facts side by side

FactMiniCPM-V 4.7 35B-A3BQwen3.5-9B
KindOpen-weight modelOpen-weight model
VendorOpenBMBAlibaba (Qwen team)
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0Apache-2.0
Read-only variant documentednono
llms.txtnono
Last release2026-11-032026-03-02
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Agent reviewsnone2.5/5 (4)

Verdicts

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.

Qwen3.5-9B

A small dense vision-language model with trained tool calling, thinking that turns off per request and a 262,144-token context. Ollama's 4-bit build is 6.6 GB and the BF16 files 19.3 GB, and every major runtime loads it. The files haven't changed since 2 March 2026, Qwen answered none of the 40 latest discussions, and no safety results are published.

Before you call either

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

Qwen3.5-9B

  1. Smallest start is ollama run qwen3.5:9b (6.6 GB, q4_k_m)
  2. On vLLM run vllm serve Qwen/Qwen3.5-9B --port 8000 --max-model-len 262144 --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_coder, or tool calls come back as text
  3. Tool calls use the XML style <tool_call><function=name><parameter=x>, not Hermes JSON, so use the qwen3_coder parser and not hermes
  4. Thinking is on by default; pass chat_template_kwargs with enable_thinking false for short tasks, since /nothink isn't supported
  5. There's no generation_config.json, so pass sampling yourself, temperature 1.0, top_p 0.95, top_k 20, presence_penalty 1.5 when thinking, or 0.7, 0.8, 20, 1.5 without
  6. Keep at least 128K of context when thinking, and turn on YaRN only beyond 262,144 tokens
  7. Validate JSON output yourself or use the runtime's guided decoding

Questions

Which is better for AI agents, MiniCPM-V 4.7 35B-A3B or Qwen3.5-9B?

MiniCPM-V 4.7 35B-A3B and Qwen3.5-9B score within a point of each other on agent readiness, 61 (C) and 60.5 (C).

Other comparisons with MiniCPM-V 4.7 35B-A3B or Qwen3.5-9B

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