Sign in

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

Cola2 vs occamy-1.0

occamy-1.0 scores 61 (C) on agent readiness against Cola2's 33.9 (F), and leads in every scored category. 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

Cola2ByteDance (Seed) · Open-weight model F33.9/100#160 of 160 open-weight models occamy-1.0Accio (Accio-Lab) · Open-weight model C61/100#59 of 160 open-weight models

Which one, for what

Cola2 F

Best for Researchers working on latent or diffusion language models who want a checkpoint to study

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

Watch for

No licence stated for the weights

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, 90 against 25
  • Risk, 55 against 40
  • Agent interface, 70 against 20
  • Documentation and upkeep, 74 against 58

Watch for

No safety results, prompt-injection 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 occamy-1.0 +65

Cola2 25

Memory 15, the only build is the F32 safetensors set, 35.07 GB, and 35.07 GB × 1.2 = 42.1 GB, within 64 GB. Loaded as BF16, as the card's example does, it needs about half, but the line reads the file size. Runtimes 0, none of the six runs it in a released version. Builds 0, one set of weights and no quantised build. Terms 0, no licence for the weights. Download 10, the Hub API reports gated false on 10 November 2026, so the files download with no account and nothing to accept. Hosted 0, Hugging Face maps no inference provider to it, and nothing names an API that serves it. 15 + 0 + 0 + 0 + 10 + 0 = 25.

occamy-1.0 90

Memory 25 of 30, Accio's MLX mxfp4 build is 18.4 GB, 22.1 GB with a fifth added, and its IQ4_XS GGUF needs 22.5 GB, both within 24 GB. Runtimes 25, the most the line gives, it keeps the base's qwen3_5_moe architecture, which llama.cpp, vLLM, SGLang and Transformers run in released versions, and Ollama v0.40.14 builds a llama.cpp (b11963) that has it. Builds 15, FP8, NVFP4, GGUF and MLX from Accio. Terms 15, Apache 2.0 like its base. Download 10, nothing is gated. Hosted 0, no API or inference provider serves it. 25 + 25 + 15 + 15 + 10 + 0 = 90.

Agent interface occamy-1.0 +50

Cola2 20

Chat template 20, A chat template in tokenizer_config.json (4,116 characters), which came with the Qwen3 tokenizer. Tool-calling format 0, none. Trained tool calling 0, not trained for tool calling. Structured output 0, Nothing about JSON or schema-constrained output. Reasoning control 0, no reasoning mode. Context 0, no context length is stated. 20 + 0 + 0 + 0 + 0 + 0 = 20.

occamy-1.0 70

Chat template 20, the base's Jinja template in the repository. Tool-calling format 10 of 25, the card names the parser but the format lives only in the template. Trained tool calling 20, trained on tool use with several calls a turn. Structured output 0, not documented. Reasoning control 10, enable_thinking per request and the card says to keep the returned reasoning content. Context 10, 262,144 tokens.

Documentation and upkeep occamy-1.0 +16

Cola2 58

Model card 8, Intended use and limitations (the out-of-scope list, and the unconverged latent model) and the architecture are on the card and the GitHub model card it links. Training data 15, the GitHub model card names the source (OLMo 2 pretraining text, retokenised) and the mix by stage with token counts, 346.03B in all. Last change 20, All six commits are from 6 November 2026, four days before this check, the last one updating a checksum in the README. Responsiveness 0, no discussions on the repository, so nobody has asked anything yet and the line reads as none answered, as settled in calibration. Version policy 5, A first release. File health 10, Config, files and card agree: F32 weights, a float32 config and a card that says to load them as bfloat16, with SHA256SUMS to check the download. 8 + 15 + 20 + 0 + 5 + 10 = 58.

occamy-1.0 74

Model card 14 of 20, languages and a knowledge cut-off are missing. Training data 15, the mix by type with token counts, the method and a published subset, without a cut-off. Last change 20, Accio's GGUF build card changed on 19 October 2026 and the main card on 2 October. Responsiveness 10, Accio answered 4 of 9 questions. Version policy 5, a first release with no files replaced. File health 10, the files agree with the card. 14 + 15 + 20 + 10 + 5 + 10 = 74.

Risk occamy-1.0 +15

Cola2 40

File safety 15, safetensors only, no .bin, .pt or .pth files (25). Provenance 15, the files sit in the ByteDance-Seed organisation, which the ByteDance-Seed GitHub repository for the model links to (10). Safety evaluation 0, no safety results. Agent guidance 5, General cautions in the GitHub model card: not instruction-tuned or safety-aligned, not for use as an assistant, for facts or advice, or for high-impact decisions about people. Licence risk 0, With no licence for the weights there is nothing to hold ByteDance to. Security programme 5, the GitHub repository's SECURITY.md sends reports to ByteDance's security centre and says how they're assessed (5). 15 + 15 + 0 + 5 + 0 + 5 = 40.

occamy-1.0 55

File safety 25, safetensors only and nothing from the repository runs to load it or build prompts. Provenance 15, the files are in the organisation Accio's GitHub links, with MD5 sums and SHA-256 for every file. Safety evaluation 0, none published. Agent guidance 0. Licence risk 15, plain Apache 2.0 that hasn't changed. Security programme 0, bug reports go to public GitHub issues and there's no security contact.

Score by category

CategoryWeight this runCola2occamy-1.0Edge
Capability35%pendingpendingpendingnot scored in this run
Reach25%252590occamy-1.0 +65
Risk20%204055occamy-1.0 +15
Agent interface10%102070occamy-1.0 +50
Documentation and upkeep10%105874occamy-1.0 +16
Negative events≤1500
TotalF 33.9/100C 61/100

Facts side by side

FactCola2occamy-1.0
KindOpen-weight modelOpen-weight model
VendorByteDance (Seed)Accio (Accio-Lab)
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceNone stated for the weights (the code is Apache 2.0)Apache-2.0
Read-only variant documentednono
llms.txtnono
Last release2026-11-062026-10-02
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Agent reviewsnone3/5 (4)

How the scores have moved

Cola2

No score change since it was listed.

occamy-1.0

Verdicts

Cola2

A research release, and an honest one: ByteDance Seed says it's a base model with an unconverged latent stage, scoring below Llama-3-8B on its own table. It's here for people studying continuous-latent generation. Agents can't use it as a model: 32-token completions, no chat or tools, the repository's own code to load it, and no licence on the weights.

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

Cola2

  1. Don't plan to use this as your model. It completes short prompts and wasn't tuned to follow instructions
  2. Don't use it commercially on the strength of this listing. The weights have no stated licence
  3. If you study it, read modeling_cola2.py first: trust_remote_code runs it
  4. Pin Transformers below 5, as the card requires
  5. Pass a seeded torch.Generator to generate(). Output varies between runs even with greedy decoding
  6. Check the download with sha256sum -c SHA256SUMS

occamy-1.0

  1. 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
  2. BF16 is 70.2 GB, so on a 128 GB machine run it without the card's 8-way tensor parallelism
  3. Keep the whole assistant message, reasoning and tool calls included, in later turns, as the card says
  4. Sampling per the card is temperature 1.0, top_p 0.95, top_k 20 and presence_penalty 1.5
  5. With the GGUFs, NFC-normalise input text and read TOKENIZER.md, since the files store qwen2 pre-tokenizer metadata
  6. The base's MTP layer isn't in this checkpoint, Accio-Lab/occamy-1.0-MTP is an experimental separate head
  7. Ollama has no Occamy library entry, so load Accio's GGUF in Ollama 0.40.14 or later, which builds a llama.cpp with the qwen35moe architecture

Questions

Which is better for AI agents, Cola2 or occamy-1.0?

occamy-1.0 scores 61 (C) on agent readiness against Cola2's 33.9 (F), and leads in every scored category.

Other comparisons with Cola2 or occamy-1.0

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