Sign in

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

MiniCPM-V 4.7 35B-A3B vs Qwen3.8-Flash-Next

Qwen3.8-Flash-Next and MiniCPM-V 4.7 35B-A3B score within a point of each other on agent readiness, 61.8 (C) and 61 (C). MiniCPM-V 4.7 35B-A3B leads on reach, risk 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

MiniCPM-V 4.7 35B-A3BOpenBMB · Open-weight model C61/100#77 of 160 open-weight models Qwen3.8-Flash-NextAlibaba (Qwen team) · Open-weight model C61.8/100#34 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 65
  • Risk, 55 against 45
  • Documentation and upkeep, 68 against 36

Watch for

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

Qwen3.8-Flash-Next C

Best for Teams with a multi-GPU server or a 128 GB Mac who want Qwen's newest sparse architecture for agentic coding and multimodal work, and aren't a hosted-model or coding-assistant business.

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

Watch for

No build fits the reference machine's 107.4 GB, and Ollama's smallest Linux build is 120 GB

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 +32

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.

Qwen3.8-Flash-Next 36

Model card 11 of 20, intended use, architecture, parameters and context are there, but limitations, languages and a knowledge cut-off aren't. Training data 0, not described beyond a token count relative to an earlier model. Last change 15, the FP8 config fix on 31 August 2026, 63 days before 2 November. Responsiveness 0, Qwen answered none of the 40 most recent questions and reports (29 to 79, 27 August to 26 October), its only reply came in the first week. Version policy 5, a first release with nothing replaced. File health 5, the files agree with the card, but a 19 October report about the template and a pull request to fix it still wait without a reply. 11 + 0 + 15 + 0 + 5 + 5 = 36.

Reach MiniCPM-V 4.7 35B-A3B +25

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.

Qwen3.8-Flash-Next 65

Memory 5 of 30, the smallest listed 4-bit build is Ollama's 120 GB q4_K_M, 144 GB with a fifth added, which is beyond the reference machine and inside 256 GB. Ollama's Apple-only 105 GB MLX build isn't among the builds and would land in the same band. Runtimes 25, released versions of llama.cpp, Ollama, vLLM, SGLang and Transformers all run the qwen4_exp architecture. Builds 10 of 15, Alibaba's only quantised build is FP8. Terms 10 of 15, a custom licence that's free for commercial use except for model-as-a-service and coding or office assistant businesses, which need a separate licence. Download 10, neither repository is gated. Hosted 5, Hugging Face lists two live providers, Featherless AI for the BF16 repository and Nscale for the FP8 build, and Alibaba's Qwen Cloud serves Qwen3.8-Flash, which the card says is based on these weights.

Risk MiniCPM-V 4.7 35B-A3B +10

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.

Qwen3.8-Flash-Next 45

File safety 25, safetensors only and nothing from the repository runs to load it or build prompts. Provenance 15, the files are in the Qwen organisation that Qwen's GitHub links to, and every file has a checksum. Safety evaluation 0, none published on the card or in the technical report. Agent guidance 0, nothing on prompt injection, refusals or safeguards. Licence risk 5 of 15, 5 off for the field-of-use limit on model-as-a-service and coding or office assistant businesses and 5 off for the naming duty above a user or revenue threshold. Security programme 0, no security.txt, disclosure policy or security contact for Qwen was found, and Alibaba's group security centre couldn't be checked, so it's scored as absent.

Score by category

CategoryWeight this runMiniCPM-V 4.7 35B-A3BQwen3.8-Flash-NextEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%259065MiniCPM-V 4.7 35B-A3B +25
Risk20%205545MiniCPM-V 4.7 35B-A3B +10
Agent interface10%107070even
Documentation and upkeep10%106836MiniCPM-V 4.7 35B-A3B +32
Negative events≤1500
TotalC 61/100C 61.8/100

Facts side by side

FactMiniCPM-V 4.7 35B-A3BQwen3.8-Flash-Next
KindOpen-weight modelOpen-weight model
VendorOpenBMBAlibaba (Qwen team)
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0Qwen Community License 1.0 (custom, not an OSI licence). Free of charge, the model name shown in products above 100M monthly users or US$20M monthly revenue, and a separate licence from Qwen before commercial use by a Model as a Service or AI Work Assistant business
Read-only variant documentednono
llms.txtnono
Last release2026-11-032026-08-31
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Agent reviewsnone2/5 (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.

Qwen3.8-Flash-Next

A large sparse cousin with 6B active parameters for agentic coding and multimodal work, previewing Qwen's next architecture. It needs a 128 GB Mac for Ollama's MLX build or about 144 GB for the 4-bit GGUF, and Qwen Cloud serves it. The main risk is a licence that needs a separate deal for hosted-model and coding or office assistant businesses.

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

Qwen3.8-Flash-Next

  1. On a 128 GB Mac start it with ollama run qwen3.8-flash-next:125b-mlx (105 GB, NVFP4), on Linux the smallest Ollama build is qwen3.8-flash-next:125b-a6b-q4_K_M at 120 GB, which won't fit a 107.4 GB GPU share
  2. On a server, vllm serve Qwen/Qwen3.8-Flash-Next-FP8 --tensor-parallel-size 4 --max-model-len 262144 --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_coder
  3. Use the qwen3_coder tool parser and the qwen3 reasoning parser, as Qwen's GitHub README does
  4. Thinking is on by default, pass chat_template_kwargs with enable_thinking false to skip it, and read the reasoning from reasoning_content, even though SGLang's cookbook says thinking can't be turned off
  5. reasoning_effort takes xhigh (default), medium or low, and any other value makes the template raise an error
  6. Send at most one system message and put it first, since the template raises an error otherwise
  7. Sampling per the card is temperature 1.0 and top_p 0.95 when thinking, temperature 0.7, top_p 0.8 and presence_penalty 1.5 without
  8. vLLM keeps the 51B n-gram table in host memory on 80 GB GPUs by default, per its recipe
  9. Validate JSON output yourself or use the runtime's guided decoding, since structured output isn't documented
  10. Read the Qwen Community License before serving it to others as an API or inside a coding or office assistant product

Questions

Which is better for AI agents, MiniCPM-V 4.7 35B-A3B or Qwen3.8-Flash-Next?

Qwen3.8-Flash-Next and MiniCPM-V 4.7 35B-A3B score within a point of each other on agent readiness, 61.8 (C) and 61 (C). MiniCPM-V 4.7 35B-A3B leads on reach, risk and documentation and upkeep.

Other comparisons with MiniCPM-V 4.7 35B-A3B or Qwen3.8-Flash-Next

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