Head to head · Open-weight models you run yourself · October 2026 research run
OTel-2.0-LLM-31B-IT vs ZAYA1-8B
ZAYA1-8B scores 61 (C) on agent readiness against OTel-2.0-LLM-31B-IT's 56.8 (C), and leads in 1 of 4 scored categories. OTel-2.0-LLM-31B-IT leads on 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
Which one, for what
Best for Telecoms teams that want an open model for standards questions and RAG on their own hardware
Ahead on
- Documentation and upkeep, 74 against 50
Watch for
BF16 only at 62.6 GB, with no GGUF or other quantised build from anyone we checked
ZAYA1-8B C
Best for People who want a small, fast reasoning model for maths and code and can live without tool calling
Ahead on
- Reach, 80 against 50
Watch for
Tool calling needs a parser that only Zyphra's vLLM fork has
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 ZAYA1-8B +30
OTel-2.0-LLM-31B-IT 50
Memory 10, the publisher's only build is the BF16 safetensors, 62.55 GB for the 15 shards the index names, and 62.55 GB × 1.2 = 75.1 GB, above 64 GB and inside the reference machine's GPU share. Runtimes 15, the architecture is Gemma4ForConditionalGeneration, which vLLM 0.33.0, SGLang 0.5.23 and Transformers 5.22.2 run from the safetensors files, three at 5 each. Builds 0, the publisher ships the BF16 weights only. Terms 15, Apache 2.0 in the card's metadata, an OSI licence, with nothing added on the card. Download 10, gated is false on 10 November 2026, so the files download with no account or terms. Hosted 0, Hugging Face maps one inference provider, Featherless AI (live), short of the two the line needs. 10 + 15 + 0 + 15 + 10 + 0 = 50.
ZAYA1-8B 80
Memory 30, the smallest build from Zyphra is the MXFP4-Experts repository, 5.85 GB, and 5.85 GB × 1.2 = 7.0 GB, within 16 GB. Runtimes 10, Released Transformers 5.22.2 has the zaya model and SGLang 0.5.23 has srt/models/zaya.py. Builds 15, Quantised builds from Zyphra at two precisions, FP8 and MXFP4 for the experts, each in its own repository. Terms 15, Apache 2.0 in the card's metadata, an OSI licence with nothing added. Download 10, the Hub API reports gated false for the model and its builds 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 the card names no API. Zyphra's site lists a cloud product for its open models, which wasn't checked for this model. 30 + 10 + 15 + 15 + 10 + 0 = 80.
Documentation and upkeep OTel-2.0-LLM-31B-IT +24
OTel-2.0-LLM-31B-IT 74
Model card 14, Intended use, a long limitations section, the architecture and training method, the parameters (31B) and the language (English) are on the card. Training data 15, the card names the sources (3GPP, ETSI, ITU, GSMA, CAMARA, O-RAN and TM Forum material provided by GSMA), the overall sizes (15 billion raw tokens, over 1 trillion processed, about 440 billion used), the mix of example types and the processing tool, and lists what was left out. Last change 20, the last commit, on 1 November 2026, updated the card's links, resources, citation and contacts, nine days before this check. Responsiveness 20, Of the 3 discussions that aren't pull requests (7 August to 28 October 2026), 2 have a reply from the repository's owner, which is most. Version policy 0, the weights were replaced in place: uploads on 27 July, 3 August and 1 September 2026 under one name, with a standing notice on the card that they may change and that users should pin a revision, and no dated note of what changed. File health 5, the card describes 15 shards of about 62.6 GB while the repository still holds an earlier 14-shard set beside them, 126.8 GB in all. 14 + 15 + 20 + 20 + 0 + 5 = 74.
ZAYA1-8B 50
Model card 5, Intended use and the parameter counts are on the card. Training data 0, Nothing on the card about the training data. Last change 10, the main repository last changed on 26 June 2026 (the checkpoint reshaped for Transformers), 137 days before this check, and the quantised repositories on 2 July, 131 days. Responsiveness 20, Of the 16 most recent discussions that aren't pull requests (7 May to 14 August 2026), 10 have a reply from a Zyphra member, which is most. Version policy 5, the original checkpoint is kept as ZAYA1-8B-legacy and the card says so at the top, without a date. File health 10, Config, template and card agree on the architecture after the reshape. 5 + 0 + 10 + 20 + 5 + 10 = 50.
Score by category
| Category | Weight this run | OTel-2.0-LLM-31B-IT | ZAYA1-8B | Edge |
|---|---|---|---|---|
| Capability | 35%pending | pending | pending | not scored in this run |
| Reach | 25%25 | 50 | 80 | ZAYA1-8B +30 |
| Risk | 20%20 | 55 | 55 | even |
| Agent interface | 10%10 | 60 | 60 | even |
| Documentation and upkeep | 10%10 | 74 | 50 | OTel-2.0-LLM-31B-IT +24 |
| Negative events | ≤15 | 0 | 0 | |
| Total | C 56.8/100 | C 61/100 |
Facts side by side
| Fact | OTel-2.0-LLM-31B-IT | ZAYA1-8B |
|---|---|---|
| Kind | Open-weight model | Open-weight model |
| Vendor | AT&T (Open Telco AI) | Zyphra |
| 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 | no | no |
| Last release | 2026-11-01 | 2026-07-02 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
Verdicts
OTel-2.0-LLM-31B-IT
A real telecoms post-training of Gemma 4 31B IT with an unusually candid card on what was and wasn't trained. It fits a 128 GB machine in BF16 only, with no quantised build, sits in a personal account, and its weights have been replaced in place. Tool-call format, structured output and safety results aren't documented.
ZAYA1-8B
A small reasoning model trained from scratch by one lab, with a clean licence, 4-bit and FP8 builds and a team that answers questions. It's the hardest of the small models to run: its own architecture, a card that points at forks, and tool calling that needs a parser no release has. Little on limits, data or safety.
Before you call either
OTel-2.0-LLM-31B-IT
- Download the 15 shards the index names, not the whole repository, which is twice the size
- Pin a revision. The card says the weights may change under the same name
- Serve it with vLLM 0.19.0 or later and the repository's own chat template, not Gemma 4's
- Send no thinking flags. It answers directly and wasn't trained on Gemma's thought channel
- Use it as the generation stage of a RAG pipeline over telecom standards, with source attribution and human review
- Don't use it to run network tools unattended. The card says that hasn't been evaluated
ZAYA1-8B
- Use it for reasoning, maths and code. Don't count on tool calling outside Zyphra's vLLM fork
- Run it with Transformers 5.22.2 or SGLang 0.5.23, which have the model built in
- Use temperature 1.0 and top_p 0.95 in general, and temperature 0.6 for agent and code work
- Download
Zyphra/ZAYA1-8B, not the legacy repository, for the released runtimes - The quantised repositories have no licence tag. The main one is Apache 2.0
Questions
Which is better for AI agents, OTel-2.0-LLM-31B-IT or ZAYA1-8B?
ZAYA1-8B scores 61 (C) on agent readiness against OTel-2.0-LLM-31B-IT's 56.8 (C), and leads in 1 of 4 scored categories. OTel-2.0-LLM-31B-IT leads on documentation and upkeep.
Other comparisons with OTel-2.0-LLM-31B-IT or ZAYA1-8B
- Agents-A1-4B vs OTel-2.0-LLM-31B-IT
- Agents-A1-4B vs ZAYA1-8B
- Apertus v1.5 8B vs OTel-2.0-LLM-31B-IT
- Apertus v1.5 8B vs ZAYA1-8B
- Apodex-1.1-mini vs OTel-2.0-LLM-31B-IT
- Apodex-1.1-mini vs ZAYA1-8B
- Arete-27B vs OTel-2.0-LLM-31B-IT
- Arete-27B vs ZAYA1-8B
- BigBang-v1 vs OTel-2.0-LLM-31B-IT
- BigBang-v1 vs ZAYA1-8B
- Carbon-X vs OTel-2.0-LLM-31B-IT
- Carbon-X vs ZAYA1-8B
- Cola2 vs OTel-2.0-LLM-31B-IT
- Cola2 vs ZAYA1-8B
- Cosmos-Reason2-2B vs OTel-2.0-LLM-31B-IT
- Cosmos-Reason2-2B vs ZAYA1-8B
- Darwin-36B-Opus vs OTel-2.0-LLM-31B-IT
- Darwin-36B-Opus vs ZAYA1-8B
- DeepSeek-V3.2 vs OTel-2.0-LLM-31B-IT
- DeepSeek-V3.2 vs ZAYA1-8B
- DeepSeek V4.1 Flash vs OTel-2.0-LLM-31B-IT
- DeepSeek V4.1 Flash vs ZAYA1-8B
- DeepSeek-V4-Flash-0731 vs OTel-2.0-LLM-31B-IT
- DeepSeek-V4-Flash-0731 vs ZAYA1-8B
- Devstral Small 2 vs OTel-2.0-LLM-31B-IT
- Devstral Small 2 vs ZAYA1-8B
- DiffusionGemma 26B A4B IT vs OTel-2.0-LLM-31B-IT
- DiffusionGemma 26B A4B IT vs ZAYA1-8B
- EXAONE 4.5 33B vs OTel-2.0-LLM-31B-IT
- EXAONE 4.5 33B vs ZAYA1-8B
- Gemma 4 12B IT vs OTel-2.0-LLM-31B-IT
- Gemma 4 12B IT vs ZAYA1-8B
- Gemma 4 26B A4B IT vs OTel-2.0-LLM-31B-IT
- Gemma 4 26B A4B IT vs ZAYA1-8B
- Gemma 4 31B IT vs OTel-2.0-LLM-31B-IT
- Gemma 4 31B IT vs ZAYA1-8B
- Gemma 4 E2B IT vs OTel-2.0-LLM-31B-IT
- Gemma 4 E2B IT vs ZAYA1-8B
- Gemma 4 E4B IT vs OTel-2.0-LLM-31B-IT
- Gemma 4 E4B IT vs ZAYA1-8B
- GLM-4.5-Air vs OTel-2.0-LLM-31B-IT
- GLM-4.5-Air vs ZAYA1-8B
- GLM-4.7-Flash vs OTel-2.0-LLM-31B-IT
- GLM-4.7-Flash vs ZAYA1-8B
- GLM-5.3-Flash vs OTel-2.0-LLM-31B-IT
- GLM-5.3-Flash vs ZAYA1-8B
- GLM-5.3 vs OTel-2.0-LLM-31B-IT
- GLM-5.3 vs ZAYA1-8B
- gpt-oss-120b vs OTel-2.0-LLM-31B-IT
- gpt-oss-120b vs ZAYA1-8B
- gpt-oss-20b vs OTel-2.0-LLM-31B-IT
- gpt-oss-20b vs ZAYA1-8B
- Granite 4.2 30B vs OTel-2.0-LLM-31B-IT
- Granite 4.2 30B vs ZAYA1-8B
- Granite 4.2 3B vs OTel-2.0-LLM-31B-IT
- Granite 4.2 3B vs ZAYA1-8B
- Granite 4.2 8B vs OTel-2.0-LLM-31B-IT
- Granite 4.2 8B vs ZAYA1-8B
- Hy-Memory-30B-A3B vs OTel-2.0-LLM-31B-IT
- Hy-Memory-30B-A3B vs ZAYA1-8B
- Hy3 vs OTel-2.0-LLM-31B-IT
- Hy3 vs ZAYA1-8B
- Inkling-Small vs OTel-2.0-LLM-31B-IT
- Inkling-Small vs ZAYA1-8B
- Inkling vs OTel-2.0-LLM-31B-IT
- Inkling vs ZAYA1-8B
- InternVL3.5-GPT-OSS-20B-A4B-Preview vs OTel-2.0-LLM-31B-IT
- InternVL3.5-GPT-OSS-20B-A4B-Preview vs ZAYA1-8B
- Kimi K3.1 Pro vs OTel-2.0-LLM-31B-IT
- Kimi K3.1 Pro vs ZAYA1-8B
- Kimi K3 vs OTel-2.0-LLM-31B-IT
- Kimi K3 vs ZAYA1-8B
- Kolibri-1 vs OTel-2.0-LLM-31B-IT
- Kolibri-1 vs ZAYA1-8B
- Kronos vs OTel-2.0-LLM-31B-IT
- Kronos vs ZAYA1-8B
- Laguna M.1 vs OTel-2.0-LLM-31B-IT
- Laguna M.1 vs ZAYA1-8B
- Laguna S 2.1 vs OTel-2.0-LLM-31B-IT
- Laguna S 2.1 vs ZAYA1-8B
- Laguna XS 2.1 vs OTel-2.0-LLM-31B-IT
- Laguna XS 2.1 vs ZAYA1-8B
- LBS-27B vs OTel-2.0-LLM-31B-IT
- LBS-27B vs ZAYA1-8B
- LFM2.5-2.6B vs OTel-2.0-LLM-31B-IT
- LFM2.5-2.6B vs ZAYA1-8B
- LFM3-1.7B vs OTel-2.0-LLM-31B-IT
- LFM3-1.7B vs ZAYA1-8B
- LFM3-Audio-2B vs OTel-2.0-LLM-31B-IT
- LFM3-Audio-2B vs ZAYA1-8B
- LFM3-Omni-2B vs OTel-2.0-LLM-31B-IT
- LFM3-Omni-2B vs ZAYA1-8B
- LFM3-VL-2B vs OTel-2.0-LLM-31B-IT
- LFM3-VL-2B vs ZAYA1-8B
- Ling-3.0-tiny vs OTel-2.0-LLM-31B-IT
- Ling-3.0-tiny vs ZAYA1-8B
- Ling-3.1-flash-1019 vs OTel-2.0-LLM-31B-IT
- Ling-3.1-flash-1019 vs ZAYA1-8B
- LongCat-2.5 vs OTel-2.0-LLM-31B-IT
- LongCat-2.5 vs ZAYA1-8B
- MiMo-V2.6 Distill Qwen 9B vs OTel-2.0-LLM-31B-IT
- MiMo-V2.6 Distill Qwen 9B vs ZAYA1-8B
- MiMo-V2.6-Flash-RL vs OTel-2.0-LLM-31B-IT
- MiMo-V2.6-Flash-RL vs ZAYA1-8B
- MiniCPM-o 4.5 vs OTel-2.0-LLM-31B-IT
- MiniCPM-o 4.5 vs ZAYA1-8B
- MiniCPM-V 4.7 1B vs OTel-2.0-LLM-31B-IT
- MiniCPM-V 4.7 1B vs ZAYA1-8B
- MiniCPM-V 4.7 35B-A3B vs OTel-2.0-LLM-31B-IT
- MiniCPM-V 4.7 35B-A3B vs ZAYA1-8B
- MiniCPM5-2B vs OTel-2.0-LLM-31B-IT
- MiniCPM5-2B vs ZAYA1-8B
- MiniMax-M2.5 vs OTel-2.0-LLM-31B-IT
- MiniMax-M2.5 vs ZAYA1-8B
- MiniMax-M2.7 vs OTel-2.0-LLM-31B-IT
- MiniMax-M2.7 vs ZAYA1-8B
- MiniMax-M3.1-Flash vs OTel-2.0-LLM-31B-IT
- MiniMax-M3.1-Flash vs ZAYA1-8B
- Mistral Large 4 vs OTel-2.0-LLM-31B-IT
- Mistral Large 4 vs ZAYA1-8B
- Muse Glimmer 30B vs OTel-2.0-LLM-31B-IT
- Muse Glimmer 30B vs ZAYA1-8B
- Nanbeige4.2-3B vs OTel-2.0-LLM-31B-IT
- Nanbeige4.2-3B vs ZAYA1-8B
- Nanbeige4.3-33B vs OTel-2.0-LLM-31B-IT
- Nanbeige4.3-33B vs ZAYA1-8B
- NVIDIA Nemotron 3.5 Bolt E4B 4GB vs OTel-2.0-LLM-31B-IT
- NVIDIA Nemotron 3.5 Bolt E4B 4GB vs ZAYA1-8B
- Nemotron 3.5 Lightning 30B A3B vs OTel-2.0-LLM-31B-IT
- Nemotron 3.5 Lightning 30B A3B vs ZAYA1-8B
- Nemotron 3 Nano 30B A3B vs OTel-2.0-LLM-31B-IT
- Nemotron 3 Nano 30B A3B vs ZAYA1-8B
- Nemotron 3 Nano 4B vs OTel-2.0-LLM-31B-IT
- Nemotron 3 Nano 4B vs ZAYA1-8B
- Nemotron 3 Nano Omni 30B A3B Reasoning vs OTel-2.0-LLM-31B-IT
- Nemotron 3 Nano Omni 30B A3B Reasoning vs ZAYA1-8B
- Nemotron 3 Super 120B A12B vs OTel-2.0-LLM-31B-IT
- Nemotron 3 Super 120B A12B vs ZAYA1-8B
- Nemotron 3 Ultra 550B A55B vs OTel-2.0-LLM-31B-IT
- Nemotron 3 Ultra 550B A55B vs ZAYA1-8B
- North Mini Code 1.0 vs OTel-2.0-LLM-31B-IT
- North Mini Code 1.0 vs ZAYA1-8B
- occamy-1.0 vs OTel-2.0-LLM-31B-IT
- occamy-1.0 vs ZAYA1-8B
- Olmo 3 7B Think vs OTel-2.0-LLM-31B-IT
- Olmo 3 7B Think vs ZAYA1-8B
- Ornith-1.5-122B vs OTel-2.0-LLM-31B-IT
- Ornith-1.5-122B vs ZAYA1-8B
- Ornith-1.5-35B-A3B vs OTel-2.0-LLM-31B-IT
- Ornith-1.5-35B-A3B vs ZAYA1-8B
- Ornith-1.5-397B vs OTel-2.0-LLM-31B-IT
- Ornith-1.5-397B vs ZAYA1-8B
- Ornith-1.5-9B vs OTel-2.0-LLM-31B-IT
- Ornith-1.5-9B vs ZAYA1-8B
- OTel-2.0-LLM-31B-IT vs Qwen-AgentWorld-35B-A3B
- OTel-2.0-LLM-31B-IT vs Qwen3-30B-A3B-Instruct-2507
- OTel-2.0-LLM-31B-IT vs Qwen3-4B-Instruct-2507
- OTel-2.0-LLM-31B-IT vs Qwen3.5-0.8B
- OTel-2.0-LLM-31B-IT vs Qwen3.5-122B-A10B
- OTel-2.0-LLM-31B-IT vs Qwen3.5-2B
- OTel-2.0-LLM-31B-IT vs Qwen3.5-397B-A17B
- OTel-2.0-LLM-31B-IT vs Qwen3.5-4B
- OTel-2.0-LLM-31B-IT vs Qwen3.5-9B
- OTel-2.0-LLM-31B-IT vs Qwen3.6-27B
- OTel-2.0-LLM-31B-IT vs Qwen3.6-35B-A3B
- OTel-2.0-LLM-31B-IT vs Qwen3.8-27B
- OTel-2.0-LLM-31B-IT vs Qwen3.8-Flash-Next
- OTel-2.0-LLM-31B-IT vs Qwen3-Coder-30B-A3B-Instruct
- OTel-2.0-LLM-31B-IT vs Qwen3-Coder-Next
- OTel-2.0-LLM-31B-IT vs Qwen3-Omni-30B-A3B-Instruct
- OTel-2.0-LLM-31B-IT vs Qwen3-VL-2B-Instruct
- OTel-2.0-LLM-31B-IT vs Qwen3-VL-30B-A3B-Instruct
- OTel-2.0-LLM-31B-IT vs Qwen3-VL-32B-Instruct
- OTel-2.0-LLM-31B-IT vs Qwen3-VL-4B-Instruct
- OTel-2.0-LLM-31B-IT vs Qwen3-VL-8B-Instruct
- OTel-2.0-LLM-31B-IT vs Qwopus3.8-27B-Flash-V2
- OTel-2.0-LLM-31B-IT vs Recursive Flint
- OTel-2.0-LLM-31B-IT vs Ripple-65B Preview
- OTel-2.0-LLM-31B-IT vs SenseNova-Loop-9B-Preview
- OTel-2.0-LLM-31B-IT vs SmolLM3-3B
- OTel-2.0-LLM-31B-IT vs Spark-X2.6-4B
- OTel-2.0-LLM-31B-IT vs Step 3.7 Flash
- OTel-2.0-LLM-31B-IT vs Swift 1.5 Qwen3.8-27B
- OTel-2.0-LLM-31B-IT vs Swift 1.5 Qwen3.8-Flash-Next
- OTel-2.0-LLM-31B-IT vs ThinkingCap (Qwen3.8 27B)
- OTel-2.0-LLM-31B-IT vs Baidu Unlimited-OCR-2
- OTel-2.0-LLM-31B-IT vs WeVisOne-VL-2B
- OTel-2.0-LLM-31B-IT vs WeVisOne-VL-4B
- Qwen-AgentWorld-35B-A3B vs ZAYA1-8B
- Qwen3-30B-A3B-Instruct-2507 vs ZAYA1-8B
- Qwen3-4B-Instruct-2507 vs ZAYA1-8B
- Qwen3.5-0.8B vs ZAYA1-8B
- Qwen3.5-122B-A10B vs ZAYA1-8B
- Qwen3.5-2B vs ZAYA1-8B
- Qwen3.5-397B-A17B vs ZAYA1-8B
- Qwen3.5-4B vs ZAYA1-8B
- Qwen3.5-9B vs ZAYA1-8B
- Qwen3.6-27B vs ZAYA1-8B
- Qwen3.6-35B-A3B vs ZAYA1-8B
- Qwen3.8-27B vs ZAYA1-8B
- Qwen3.8-Flash-Next vs ZAYA1-8B
- Qwen3-Coder-30B-A3B-Instruct vs ZAYA1-8B
- Qwen3-Coder-Next vs ZAYA1-8B
- Qwen3-Omni-30B-A3B-Instruct vs ZAYA1-8B
- Qwen3-VL-2B-Instruct vs ZAYA1-8B
- Qwen3-VL-30B-A3B-Instruct vs ZAYA1-8B
- Qwen3-VL-32B-Instruct vs ZAYA1-8B
- Qwen3-VL-4B-Instruct vs ZAYA1-8B
- Qwen3-VL-8B-Instruct vs ZAYA1-8B
- Qwopus3.8-27B-Flash-V2 vs ZAYA1-8B
- Recursive Flint vs ZAYA1-8B
- Ripple-65B Preview vs ZAYA1-8B
- SenseNova-Loop-9B-Preview vs ZAYA1-8B
- SmolLM3-3B vs ZAYA1-8B
- Spark-X2.6-4B vs ZAYA1-8B
- Step 3.7 Flash vs ZAYA1-8B
- Swift 1.5 Qwen3.8-27B vs ZAYA1-8B
- Swift 1.5 Qwen3.8-Flash-Next vs ZAYA1-8B
- ThinkingCap (Qwen3.8 27B) vs ZAYA1-8B
- Baidu Unlimited-OCR-2 vs ZAYA1-8B
- WeVisOne-VL-2B vs ZAYA1-8B
- WeVisOne-VL-4B vs ZAYA1-8B
Machine-readable
- This page as Markdown
/compare/otel-2-0-llm-31b-it-vs-zaya1-8b.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/otel-2-0-llm-31b-it.json·/api/v1/tools/zaya1-8b.json - From a terminal
anchor compare otel-2-0-llm-31b-it zaya1-8b(the CLI) - Over MCP
compare_tools {"a": "otel-2-0-llm-31b-it", "b": "zaya1-8b"}at/mcp, no key