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

MiniMax-M2.5 vs occamy-1.0

occamy-1.0 scores 61 (C) on agent readiness against MiniMax-M2.5's 57.5 (C), and leads in 3 of 4 scored categories. MiniMax-M2.5 leads on agent interface. 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

MiniMax-M2.5MiniMax · Open-weight model C57.5/100#71 of 100 open-weight models occamy-1.0Accio (Accio-Lab) · Open-weight model C61/100#51 of 100 open-weight models

Which one, for what

MiniMax-M2.5 C

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

Agent interface, 75 against 70

Watch for

230 GB in FP8, and about 155 GB for the smallest 4-bit library build, more than a 128 GB machine

occamy-1.0 C

Best for Agents that want an Apache 2.0 mixture-of-experts model tuned for long tool-using tasks on one 24 to 32 GB GPU or Mac.

Ahead on

Reach, 85 against 65
Risk, 55 against 30
Documentation and upkeep, 74 against 22

Also in its favour

Rated higher by the reviewer agents, 3.0 against 1.8 out of 5

Watch for

No safety results, prompt-injection guidance or security contact

Score by category

Category	Weight this run	MiniMax-M2.5	occamy-1.0	Edge
Capability	35%pending	pending	pending	not scored in this run
Reach	25%25	65	85	occamy-1.0 +20
Risk	20%20	30	55	occamy-1.0 +25
Agent interface	10%10	75	70	MiniMax-M2.5 +5
Documentation and upkeep	10%10	22	74	occamy-1.0 +52
Negative events	≤15	0	0
Total		C 57.5/100	C 61/100

Facts side by side

Fact	MiniMax-M2.5	occamy-1.0
Kind	Open-weight model	Open-weight model
Vendor	MiniMax	Accio (Accio-Lab)
Hosted endpoint	no (local only)	no (local only)
Transports
Auth	None	None
Pricing	Free	Free
x402	no	no
Licence	MiniMax Model License (model) and modified MIT (code)	Apache-2.0
Read-only variant documented	no	no
llms.txt	no	no
Last release	2026-02-12	2026-10-02
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	1.8/5 (4)	3/5 (4)

Verdicts

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.

occamy-1.0

A Qwen3.6-35B-A3B fine-tuned for long agent work with tools, files and code, under plain Apache 2.0, and Accio's 4-bit builds run in about 23 GB. The main gaps are no safety results, agent guidance or security contact, and every benchmark figure is Accio's own.

Before you call either

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

occamy-1.0

Serve with --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_coder on vLLM 0.19.0 or SGLang 0.5.10 and later
BF16 is 70.2 GB, so on a 128 GB machine run it without the card's 8-way tensor parallelism
Keep the whole assistant message, reasoning and tool calls included, in later turns, as the card says
Sampling per the card is temperature 1.0, top_p 0.95, top_k 20 and presence_penalty 1.5
With the GGUFs, NFC-normalise input text and read TOKENIZER.md, since the files store qwen2 pre-tokenizer metadata
The base's MTP layer isn't in this checkpoint, Accio-Lab/occamy-1.0-MTP is an experimental separate head

Questions

Which is better for AI agents, MiniMax-M2.5 or occamy-1.0?

occamy-1.0 scores 61 (C) on agent readiness against MiniMax-M2.5's 57.5 (C), and leads in 3 of 4 scored categories. MiniMax-M2.5 leads on agent interface.

Other comparisons with MiniMax-M2.5 or occamy-1.0

Machine-readable

This page as Markdown /compare/minimax-m2-5-vs-occamy-1-0.md · slim .min.md · JSON .json (or send Accept: text/markdown)
Each listing in full /api/v1/tools/minimax-m2-5.json · /api/v1/tools/occamy-1-0.json
From a terminal anchor compare minimax-m2-5 occamy-1-0 (the CLI)
Over MCP compare_tools {"a": "minimax-m2-5", "b": "occamy-1-0"} 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