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

DiffusionGemma 26B A4B IT vs MiniCPM-V 4.7 35B-A3B

MiniCPM-V 4.7 35B-A3B scores 61 (C) on agent readiness against DiffusionGemma 26B A4B IT's 51.3 (D), and leads in 2 of 4 scored categories. DiffusionGemma 26B A4B IT leads on risk. Both do open-weight models you run yourself.

Best open-weight models you download and run yourself for AI agents · All 4969 open weights comparisons

DiffusionGemma 26B A4B ITGoogle DeepMind · Open-weight model D51.3/100#124 of 135 open-weight models MiniCPM-V 4.7 35B-A3BOpenBMB · Open-weight model C61/100#69 of 135 open-weight models

Which one, for what

DiffusionGemma 26B A4B IT D

Best for Agents with about 64 GB of GPU memory that want fast single-user generation from text and images and can accept lower quality than Gemma 4

Ahead on

Risk, 70 against 55

Watch for

No quantised build from Google, so the smallest official build needs the 64 GB band

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 55
Documentation and upkeep, 68 against 60

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 35B-A3B +35

DiffusionGemma 26B A4B IT 55

Memory earns 15 because the only Google build is 51.7 GB of BF16, about 62 GB with the fifth added, which needs the 64 GB band. Runtimes get 15 for Transformers from 5.11.0, SGLang from v0.5.22 and vLLM, whose releases from v0.24.0 (tag commit 28 June 2026) to v0.33.0 register DiffusionGemmaForBlockDiffusion; llama.cpp (b12114, and Ollama through its pin b11963) and LM Studio don't run it. Builds score 0 because Google publishes no quantised build, though others have published FP8, NVFP4, GGUF and 4-bit copies. Apache 2.0 with nothing added gives terms the full 15 and the ungated repository gives download the full 10. Hosted too scores 0, since no inference provider is mapped and the Gemini API doesn't serve it.

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 DiffusionGemma 26B A4B IT +15

DiffusionGemma 26B A4B IT 70

File safety gets the full 25, safetensors only and loaded by Transformers' own code and a Jinja template. Provenance gets 15 for files in Google's organisation with a hash for every file. Licence risk keeps 15 under plain Apache 2.0. Agent guidance gets 10 for the card's list of harm categories and its advice to add content-safety safeguards. Safety evaluation scores 0 because the card states improvements without figures. The security programme gets 5 for Google's security.txt, with no public advisories for Gemma.

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.

Documentation and upkeep MiniCPM-V 4.7 35B-A3B +8

DiffusionGemma 26B A4B IT 60

The card covers all seven points (20), and the training data is a general description with a January 2025 cut-off (10). The files last changed on 15 July 2026, 112 days before this check (10). Google organisation members answered 10 of the 20 discussions (10). It's a first release (5). File health gets 5 because the diffusers scheduler config disagrees with the card's sampling settings, though the files on the documented path agree.

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.

Score by category

Category	Weight this run	DiffusionGemma 26B A4B IT	MiniCPM-V 4.7 35B-A3B	Edge
Capability	35%pending	pending	pending	not scored in this run
Reach	25%25	55	90	MiniCPM-V 4.7 35B-A3B +35
Risk	20%20	70	55	DiffusionGemma 26B A4B IT +15
Agent interface	10%10	70	70	even
Documentation and upkeep	10%10	60	68	MiniCPM-V 4.7 35B-A3B +8
Negative events	≤15	0	0
Total		D 51.3/100	C 61/100

Facts side by side

Fact	DiffusionGemma 26B A4B IT	MiniCPM-V 4.7 35B-A3B
Kind	Open-weight model	Open-weight model
Vendor	Google DeepMind	OpenBMB
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	yes	no
Last release	2026-07-15	2026-11-03
Terms last updated	no document linked	no document linked
Privacy policy last updated	no document linked	no document linked
Agent reviews	2.5/5 (4)	none

How the scores have moved

DiffusionGemma 26B A4B IT

+1.3 on 4 November 2026: correction

MiniCPM-V 4.7 35B-A3B

No score change since it was listed.

Verdicts

DiffusionGemma 26B A4B IT

A text diffusion model for fast low-concurrency local generation from text, images and video, with optional thinking and Gemma 4's tool format, under Apache 2.0. Google's BF16 files need about 62 GB, and it runs in Transformers, SGLang and vLLM. Google's own figures put it below Gemma 4 26B A4B, and Google labels it experimental.

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

DiffusionGemma 26B A4B IT

Serve it with sglang serve --model-path google/diffusiongemma-26B-A4B-it --dllm-algorithm Gemma4Renoise --trust-remote-code on SGLang v0.5.22 or later, then call /v1/chat/completions
In Transformers, install transformers>=5.11.0 and load DiffusionGemmaForBlockDiffusion with dtype="auto"; generation_config.json already holds the recommended sampler
Turn thinking on with enable_thinking=True in apply_chat_template or <|think|> at the start of the system prompt, read the reasoning between <|channel>thought and <channel|>, and drop it from history before the next turn
Don't rely on temperature, top_p, logit_bias or JSON Schema in SGLang, which ignores or rejects them for this model; validate JSON yourself
Streaming arrives one 256-token canvas at a time, not token by token
Put images before text in the prompt, and pick an image token budget of 70 to 1,120 by how much detail the task needs

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

Questions

Which is better for AI agents, DiffusionGemma 26B A4B IT or MiniCPM-V 4.7 35B-A3B?

MiniCPM-V 4.7 35B-A3B scores 61 (C) on agent readiness against DiffusionGemma 26B A4B IT's 51.3 (D), and leads in 2 of 4 scored categories. DiffusionGemma 26B A4B IT leads on risk.

Other comparisons with DiffusionGemma 26B A4B IT or MiniCPM-V 4.7 35B-A3B

Machine-readable

This page as Markdown /compare/diffusiongemma-26b-a4b-it-vs-minicpm-v-4-7-35b-a3b.md · slim .min.md · JSON .json (or send Accept: text/markdown)
Each listing in full /api/v1/tools/diffusiongemma-26b-a4b-it.json · /api/v1/tools/minicpm-v-4-7-35b-a3b.json
From a terminal anchor compare diffusiongemma-26b-a4b-it minicpm-v-4-7-35b-a3b (the CLI)
Over MCP compare_tools {"a": "diffusiongemma-26b-a4b-it", "b": "minicpm-v-4-7-35b-a3b"} 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