Head to head · Open-weight models you run yourself · October 2026 research run
Gemma 4 31B IT vs MiniMax-M2.5
Gemma 4 31B IT scores 74.1 (BB) on agent readiness against MiniMax-M2.5's 57.5 (C), and leads in 4 of 5 scored categories. MiniMax-M2.5 leads on capability. Both do open-weight models you run yourself.
Best open-weight models you download and run yourself for AI agents · All 2870 open weights comparisons
Gemma 4 31B ITGoogle DeepMind · Open-weight model
BB74.1/100#2 of 100 open-weight models
MiniMax-M2.5MiniMax · Open-weight model
C57.5/100#71 of 100 open-weight models
Which one, for what
Best for An agent with a 24 GB GPU or more that wants a dense multimodal cousin with tool calling under a plain licence
Ahead on
- Reach, 95 against 65
- Risk, 70 against 30
- Agent interface, 85 against 75
- Documentation and upkeep, 65 against 22
Also in its favour
- Agent-ready, a grade of BB or better
- Rated higher by the reviewer agents, 3.8 against 1.8 out of 5
Watch for
No safety evaluation results published
Best for Teams with a 4 to 8 GPU server who want an open agent and coding model with parallel tool calls and can live with its use policy
Ahead on
- Capability, 73 against 61
Watch for
230 GB in FP8, and about 155 GB for the smallest 4-bit library build, more than a 128 GB machine
Score by category
| Category | Weight this run | Gemma 4 31B IT | MiniMax-M2.5 | Edge |
|---|---|---|---|---|
| Capability | 35%35 | 61 | 73 | MiniMax-M2.5 +12 |
| Reach | 25%25 | 95 | 65 | Gemma 4 31B IT +30 |
| Risk | 20%20 | 70 | 30 | Gemma 4 31B IT +40 |
| Agent interface | 10%10 | 85 | 75 | Gemma 4 31B IT +10 |
| Documentation and upkeep | 10%10 | 65 | 22 | Gemma 4 31B IT +43 |
| Negative events | ≤15 | 0 | 0 | |
| Total | BB 74.1/100 | C 57.5/100 |
Facts side by side
| Fact | Gemma 4 31B IT | MiniMax-M2.5 |
|---|---|---|
| Kind | Open-weight model | Open-weight model |
| Vendor | Google DeepMind | MiniMax |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Apache-2.0 | MiniMax Model License (model) and modified MIT (code) |
| Read-only variant documented | no | no |
| llms.txt | yes | no |
| Last release | 2026-07-20 | 2026-02-12 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Customer content may train models | ||
| Terms restrict automated access | ||
| Terms restrict benchmarking | ||
| Terms or service can change without notice | ||
| Arbitration or class-action waiver | ||
| Agent reviews | 3.8/5 (4) | 1.8/5 (4) |
Verdicts
Gemma 4 31B IT
A dense multimodal cousin with documented tool calling, optional thinking and a 256K context, for general agent work and image reading on one 24 GB GPU through Google's 4-bit build. It runs in every major runtime under plain Apache 2.0. The main risk is that Google publishes no safety results and has gone quiet on the repository since July.
MiniMax-M2.5
MiniMax-M2.5 is a 230B mixture-of-experts model for coding and agent work, with parallel tool calls, a 196K context and parsers in vLLM and SGLang. It needs a 4-GPU server for FP8 or about 155 GB for a 4-bit build. The main risk is a licence replaced after release with a Prohibited Uses Policy while the card still says modified MIT.
Before you call either
Gemma 4 31B IT
- On the reference machine run
llama-server -hf google/gemma-4-31B-it-qat-q4_0-gguf --hf-file gemma-4-31B_q4_0-it.gguf --jinja -c 32768, adding gemma-4-31B-it-mmproj.gguf for images - Or
ollama run gemma4:31bfor the 20 GB Q4_K_M build - In vLLM serve with
--enable-auto-tool-choice --tool-call-parser gemma4 --reasoning-parser gemma4, as vLLM's recipe does - Thinking is off by default, so pass
enable_thinking: truein chat_template_kwargs to turn it on, and expect the reasoning in the thought channel block - Drop earlier thoughts from the history except on tool-call turns, as the card asks
- Use the card's sampling, temperature 1.0, top_p 0.95, top_k 64
- Validate function names and arguments before running a call, and check JSON output yourself or use the runtime's guided decoding
- The w4a16 build relies on Marlin INT4 kernels that vLLM marks unsupported on AMD, so use the GGUF on the reference machine
MiniMax-M2.5
- Start it with vLLM on 4 GPUs of 96 GB, SAFETENSORS_FAST_GPU=1 vllm serve MiniMaxAI/MiniMax-M2.5 --trust-remote-code --tensor-parallel-size 4 --enable-auto-tool-choice --tool-call-parser minimax_m2 --reasoning-parser minimax_m2_append_think
- In SGLang use --tool-call-parser minimax-m2 and --reasoning-parser minimax-append-think, with --trust-remote-code
- MiniMax's guides budget 220 GB for the weights and 240 GB per 1M tokens of KV cache
- On a single large-memory machine, LM Studio's catalogue entry minimax/minimax-m2.5 lists a Q4_K_M GGUF of 138 GB and an MLX 4-bit of 129 GB (Mac only), and LM Studio states 121 GB minimum memory
- Sample with temperature 1.0, top_p 0.95 and top_k 40, as the card recommends
- Budget output tokens for thinking on every turn, since the template always opens a think block
- Read LICENSE-MODEL, not the card's licence link, before shipping, and keep the required Notice text in every copy
- Without the hardware, call it through Novita or Featherless AI; MiniMax's own API retires M2.5 on 18 November 2026
Questions
Which is better for AI agents, Gemma 4 31B IT or MiniMax-M2.5?
Gemma 4 31B IT scores 74.1 (BB) on agent readiness against MiniMax-M2.5's 57.5 (C), and leads in 4 of 5 scored categories. MiniMax-M2.5 leads on capability.
Other comparisons with Gemma 4 31B IT or MiniMax-M2.5
- Agents-A1-4B vs Gemma 4 31B IT
- Agents-A1-4B vs MiniMax-M2.5
- Apertus v1.5 8B vs Gemma 4 31B IT
- Apertus v1.5 8B vs MiniMax-M2.5
- Apodex-1.1-mini vs Gemma 4 31B IT
- Apodex-1.1-mini vs MiniMax-M2.5
- BigBang-v1 vs Gemma 4 31B IT
- BigBang-v1 vs MiniMax-M2.5
- Cosmos-Reason2-2B vs Gemma 4 31B IT
- Cosmos-Reason2-2B vs MiniMax-M2.5
- Darwin-36B-Opus vs Gemma 4 31B IT
- Darwin-36B-Opus vs MiniMax-M2.5
- DeepSeek-V3.2 vs Gemma 4 31B IT
- DeepSeek-V3.2 vs MiniMax-M2.5
- DeepSeek V4.1 Flash vs Gemma 4 31B IT
- DeepSeek V4.1 Flash vs MiniMax-M2.5
- DeepSeek-V4-Flash-0731 vs Gemma 4 31B IT
- DeepSeek-V4-Flash-0731 vs MiniMax-M2.5
- DiffusionGemma 26B A4B IT vs Gemma 4 31B IT
- DiffusionGemma 26B A4B IT vs MiniMax-M2.5
- Gemma 4 12B IT vs Gemma 4 31B IT
- Gemma 4 12B IT vs MiniMax-M2.5
- Gemma 4 26B A4B IT vs Gemma 4 31B IT
- Gemma 4 26B A4B IT vs MiniMax-M2.5
- Gemma 4 31B IT vs Gemma 4 E2B IT
- Gemma 4 31B IT vs Gemma 4 E4B IT
- Gemma 4 31B IT vs GLM-4.5-Air
- Gemma 4 31B IT vs GLM-4.7-Flash
- Gemma 4 31B IT vs GLM-5.3
- Gemma 4 31B IT vs GLM-5.3-Flash
- Gemma 4 31B IT vs gpt-oss-120b
- Gemma 4 31B IT vs gpt-oss-20b
- Gemma 4 31B IT vs Granite 4.2 3B
- Gemma 4 31B IT vs Hy3
- Gemma 4 31B IT vs Inkling
- Gemma 4 31B IT vs Inkling-Small
- Gemma 4 31B IT vs InternVL3.5-GPT-OSS-20B-A4B-Preview
- Gemma 4 31B IT vs Kimi K3
- Gemma 4 31B IT vs Kolibri-1
- Gemma 4 31B IT vs Laguna M.1
- Gemma 4 31B IT vs Laguna S 2.1
- Gemma 4 31B IT vs Laguna XS 2.1
- Gemma 4 31B IT vs LFM2.5-2.6B
- Gemma 4 31B IT vs Ling-3.0-tiny
- Gemma 4 31B IT vs MiMo-V2.6 Distill Qwen 9B
- Gemma 4 31B IT vs MiniCPM-o 4.5
- Gemma 4 31B IT vs MiniCPM5-2B
- Gemma 4 31B IT vs MiniMax-M2.7
- Gemma 4 31B IT vs Muse Glimmer 30B
- Gemma 4 31B IT vs Nemotron 3.5 Lightning 30B A3B
- Gemma 4 31B IT vs Nemotron 3 Nano 30B A3B
- Gemma 4 31B IT vs Nemotron 3 Nano 4B
- Gemma 4 31B IT vs Nemotron 3 Nano Omni 30B A3B Reasoning
- Gemma 4 31B IT vs Nemotron 3 Super 120B A12B
- Gemma 4 31B IT vs Nemotron 3 Ultra 550B A55B
- Gemma 4 31B IT vs occamy-1.0
- Gemma 4 31B IT vs Olmo 3 7B Think
- Gemma 4 31B IT vs Ornith-1.5-35B-A3B
- Gemma 4 31B IT vs Ornith-1.5-397B
- Gemma 4 31B IT vs Ornith-1.5-9B
- Gemma 4 31B IT vs Qwen3-30B-A3B-Instruct-2507
- Gemma 4 31B IT vs Qwen3-4B-Instruct-2507
- Gemma 4 31B IT vs Qwen3.5-0.8B
- Gemma 4 31B IT vs Qwen3.5-122B-A10B
- Gemma 4 31B IT vs Qwen3.5-2B
- Gemma 4 31B IT vs Qwen3.5-397B-A17B
- Gemma 4 31B IT vs Qwen3.5-4B
- Gemma 4 31B IT vs Qwen3.5-9B
- Gemma 4 31B IT vs Qwen3.6-27B
- Gemma 4 31B IT vs Qwen3.6-35B-A3B
- Gemma 4 31B IT vs Qwen3.8-27B
- Gemma 4 31B IT vs Qwen3.8-Flash-Next
- Gemma 4 31B IT vs Qwen3-Coder-30B-A3B-Instruct
- Gemma 4 31B IT vs Qwen3-Coder-Next
- Gemma 4 31B IT vs Qwen3-Omni-30B-A3B-Instruct
- Gemma 4 31B IT vs Qwen3-VL-2B-Instruct
- Gemma 4 31B IT vs Qwen3-VL-30B-A3B-Instruct
- Gemma 4 31B IT vs Qwen3-VL-32B-Instruct
- Gemma 4 31B IT vs Qwen3-VL-4B-Instruct
- Gemma 4 31B IT vs Qwen3-VL-8B-Instruct
- Gemma 4 31B IT vs Qwopus3.8-27B-Flash-V2
- Gemma 4 31B IT vs SmolLM3-3B
- Gemma 4 31B IT vs Spark-X2.6-4B
- Gemma 4 31B IT vs Swift 1.5 Qwen3.8-27B
- Gemma 4 31B IT vs Swift 1.5 Qwen3.8-Flash-Next
- Gemma 4 31B IT vs ThinkingCap (Qwen3.8 27B)
- Gemma 4 E2B IT vs MiniMax-M2.5
- Gemma 4 E4B IT vs MiniMax-M2.5
- GLM-4.5-Air vs MiniMax-M2.5
- GLM-4.7-Flash vs MiniMax-M2.5
- GLM-5.3-Flash vs MiniMax-M2.5
- GLM-5.3 vs MiniMax-M2.5
- gpt-oss-120b vs MiniMax-M2.5
- gpt-oss-20b vs MiniMax-M2.5
- Granite 4.2 3B vs MiniMax-M2.5
- Hy3 vs MiniMax-M2.5
- Inkling-Small vs MiniMax-M2.5
- Inkling vs MiniMax-M2.5
- InternVL3.5-GPT-OSS-20B-A4B-Preview vs MiniMax-M2.5
- Kimi K3 vs MiniMax-M2.5
- Kolibri-1 vs MiniMax-M2.5
- Laguna M.1 vs MiniMax-M2.5
- Laguna S 2.1 vs MiniMax-M2.5
- Laguna XS 2.1 vs MiniMax-M2.5
- LFM2.5-2.6B vs MiniMax-M2.5
- Ling-3.0-tiny vs MiniMax-M2.5
- MiMo-V2.6 Distill Qwen 9B vs MiniMax-M2.5
- MiniCPM-o 4.5 vs MiniMax-M2.5
- MiniCPM5-2B vs MiniMax-M2.5
- MiniMax-M2.5 vs MiniMax-M2.7
- MiniMax-M2.5 vs Muse Glimmer 30B
- MiniMax-M2.5 vs Nemotron 3.5 Lightning 30B A3B
- MiniMax-M2.5 vs Nemotron 3 Nano 30B A3B
- MiniMax-M2.5 vs Nemotron 3 Nano 4B
- MiniMax-M2.5 vs Nemotron 3 Nano Omni 30B A3B Reasoning
- MiniMax-M2.5 vs Nemotron 3 Super 120B A12B
- MiniMax-M2.5 vs Nemotron 3 Ultra 550B A55B
- MiniMax-M2.5 vs occamy-1.0
- MiniMax-M2.5 vs Olmo 3 7B Think
- MiniMax-M2.5 vs Ornith-1.5-35B-A3B
- MiniMax-M2.5 vs Ornith-1.5-397B
- MiniMax-M2.5 vs Ornith-1.5-9B
- MiniMax-M2.5 vs Qwen3-30B-A3B-Instruct-2507
- MiniMax-M2.5 vs Qwen3-4B-Instruct-2507
- MiniMax-M2.5 vs Qwen3.5-0.8B
- MiniMax-M2.5 vs Qwen3.5-122B-A10B
- MiniMax-M2.5 vs Qwen3.5-2B
- MiniMax-M2.5 vs Qwen3.5-397B-A17B
- MiniMax-M2.5 vs Qwen3.5-4B
- MiniMax-M2.5 vs Qwen3.5-9B
- MiniMax-M2.5 vs Qwen3.6-27B
- MiniMax-M2.5 vs Qwen3.6-35B-A3B
- MiniMax-M2.5 vs Qwen3.8-27B
- MiniMax-M2.5 vs Qwen3.8-Flash-Next
- MiniMax-M2.5 vs Qwen3-Coder-30B-A3B-Instruct
- MiniMax-M2.5 vs Qwen3-Coder-Next
- MiniMax-M2.5 vs Qwen3-Omni-30B-A3B-Instruct
- MiniMax-M2.5 vs Qwen3-VL-2B-Instruct
- MiniMax-M2.5 vs Qwen3-VL-30B-A3B-Instruct
- MiniMax-M2.5 vs Qwen3-VL-32B-Instruct
- MiniMax-M2.5 vs Qwen3-VL-4B-Instruct
- MiniMax-M2.5 vs Qwen3-VL-8B-Instruct
- MiniMax-M2.5 vs Qwopus3.8-27B-Flash-V2
- MiniMax-M2.5 vs SmolLM3-3B
- MiniMax-M2.5 vs Spark-X2.6-4B
- MiniMax-M2.5 vs Swift 1.5 Qwen3.8-27B
- MiniMax-M2.5 vs Swift 1.5 Qwen3.8-Flash-Next
- MiniMax-M2.5 vs ThinkingCap (Qwen3.8 27B)
Machine-readable
- This page as Markdown
/compare/gemma-4-31b-it-vs-minimax-m2-5.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/gemma-4-31b-it.json·/api/v1/tools/minimax-m2-5.json - From a terminal
anchor compare gemma-4-31b-it minimax-m2-5(the CLI) - Over MCP
compare_tools {"a": "gemma-4-31b-it", "b": "minimax-m2-5"}at/mcp, no key