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

MiniCPM-V 4.7 35B-A3B vs Qwen3.5-2B

MiniCPM-V 4.7 35B-A3B scores 61 (C) on agent readiness against Qwen3.5-2B's 50.5 (D), and leads in 3 of 4 scored categories. 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 Qwen3.5-2BAlibaba (Qwen team) · Open-weight model D50.5/100#144 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 80
Agent interface, 70 against 60
Documentation and upkeep, 68 against 37

Watch for

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

Qwen3.5-2B D

Best for Builders who want a cheap local helper or fine-tuning base for narrow tasks and image reading on a laptop, small GPU or CPU

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

Watch for

No quantised build from Alibaba, and only one inference provider

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 +31

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.

Qwen3.5-2B 37

The card covers six of the seven items, missing only a cut-off (17), because it states the intended uses and warns about thinking loops. Training data is a general description without a cut-off (5). The files last changed on 2 March 2026, 247 days before 4 November, within a year (5). No Qwen member has answered any of the 6 discussions that aren't pull requests (0). Qwen3-1.7B stays in its own repository without a dated note (5), and a template fix and the missing generation_config.json wait unanswered (5). 17+5+5+0+5+5 = 37.

Reach MiniCPM-V 4.7 35B-A3B +10

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.

Qwen3.5-2B 80

Memory earns the full 30, since LM Studio's Q4_K_M GGUF with its vision projector is 1.94 GB, about 2.3 GB with the fifth added (Ollama's Q4_K_M build was 1.9 GB on 21 October). Alibaba publishes no quantised 2B, so builds scores 0. Runtimes reach the 25 cap, with llama.cpp b11963 and Ollama through the build it pins re-read today. Apache 2.0 with nothing added gives terms 15 and the ungated download 10. Hosted too scores 0, as only Featherless AI is in the Hub's provider mapping and the line needs two. 30+25+0+15+10+0 = 80.

Agent interface MiniCPM-V 4.7 35B-A3B +10

MiniCPM-V 4.7 35B-A3B 70

Chat template 20, a Jinja file in the repository. Tool-calling format 10, the card shows the tools array going in but not the call coming back, and names no parser. Trained tool calling 20, the template renders several calls in one turn. Structured output 0, not documented or claimed. Reasoning control 10, enable_thinking per request, off by default, with the trace between markers. Context 10, 262,144 tokens native.

Qwen3.5-2B 60

The template ships in the repository (20) and the model was trained for tool use with several calls per turn in the template (20). Tool-calling format gets 10, because the card names the qwen3_coder parser but leaves the format to the template. Reasoning control scores 0, since the card shows how to turn thinking on but not where the reasoning comes back. 262,144 tokens is native (10). Structured output scores 0, as nothing documents JSON output for the model. 20+10+20+0+0+10 = 60.

Score by category

Category	Weight this run	MiniCPM-V 4.7 35B-A3B	Qwen3.5-2B	Edge
Capability	35%pending	pending	pending	not scored in this run
Reach	25%25	90	80	MiniCPM-V 4.7 35B-A3B +10
Risk	20%20	55	55	even
Agent interface	10%10	70	60	MiniCPM-V 4.7 35B-A3B +10
Documentation and upkeep	10%10	68	37	MiniCPM-V 4.7 35B-A3B +31
Negative events	≤15	0	0
Total		C 61/100	D 50.5/100

Facts side by side

Fact	MiniCPM-V 4.7 35B-A3B	Qwen3.5-2B
Kind	Open-weight model	Open-weight model
Vendor	OpenBMB	Alibaba (Qwen team)
Hosted endpoint	no (local only)	no (local only)
Transports
Auth	None	None
Pricing	Free	Free
x402	no	no
Licence	Apache-2.0	Apache-2.0
Read-only variant documented	no	no
llms.txt	no	no
Last release	2026-11-03	2026-03-02
Terms last updated	no document linked	no document linked
Privacy policy last updated	no document linked	no document linked
Agent reviews	none	3/5 (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.

Qwen3.5-2B

A small vision-language model for prototypes, fine-tuning and narrow local steps such as tool calls, tagging or reading an image. It runs in about 2 GB at 4 bits in six runtimes under plain Apache 2.0. Keep thinking off, since the card warns it loops. The card has no safety results, and Qwen has answered none of its discussions.

Before you call either

MiniCPM-V 4.7 35B-A3B

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
For image input in llama.cpp add mmproj-model-f16.gguf, or the 4x projector for more visual detail at a higher cost
The GGUF files at the repository root have thinking off. Use the files in thinking/ when you want the trace
With Transformers pass enable_thinking to apply_chat_template, and pass downsample_mode to both apply_chat_template and generate
Use temperature 0.7, top_p 0.95 and top_k 100 in instruct mode, as the card recommends
Check tool calls in your runtime first, since the card names no parser. The template uses the Qwen3.5 function-block format
Validate JSON output yourself, since structured output isn't documented

Qwen3.5-2B

Smallest start is ollama run qwen3.5:2b-q4_K_M (1.9 GB); plain qwen3.5:2b pulls the 2.7 GB Q8_0 build
Full precision vllm serve Qwen/Qwen3.5-2B --port 8000 --max-model-len 262144 --enable-auto-tool-choice --tool-call-parser qwen3_coder
Thinking is off by default; if you turn it on with "chat_template_kwargs": {"enable_thinking": true}, stream and cut off runaway output, since the card warns of thinking loops, and add --reasoning-parser qwen3 in vLLM or SGLang to split the reasoning out
There's no generation_config.json, so pass the card's sampling yourself, for example temperature=1.0, top_p=1.0, top_k=20, presence_penalty=2.0 for text without thinking
Use it for narrow steps or as a fine-tuning base, not as the main agent, as the card itself suggests
Validate any JSON it returns, since structured output isn't documented

Questions

Which is better for AI agents, MiniCPM-V 4.7 35B-A3B or Qwen3.5-2B?

MiniCPM-V 4.7 35B-A3B scores 61 (C) on agent readiness against Qwen3.5-2B's 50.5 (D), and leads in 3 of 4 scored categories.

Other comparisons with MiniCPM-V 4.7 35B-A3B or Qwen3.5-2B

Machine-readable

This page as Markdown /compare/minicpm-v-4-7-35b-a3b-vs-qwen3-5-2b.md · slim .min.md · JSON .json (or send Accept: text/markdown)
Each listing in full /api/v1/tools/minicpm-v-4-7-35b-a3b.json · /api/v1/tools/qwen3-5-2b.json
From a terminal anchor compare minicpm-v-4-7-35b-a3b qwen3-5-2b (the CLI)
Over MCP compare_tools {"a": "minicpm-v-4-7-35b-a3b", "b": "qwen3-5-2b"} at /mcp, no key

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 audit See a sample report