Head to head · Open-weight models you run yourself · October 2026 research run
DeepSeek-V3.2 vs ZAYA1-8B
ZAYA1-8B scores 61 (C) on agent readiness against DeepSeek-V3.2's 58.6 (C), and leads in 3 of 4 scored categories. 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 Teams with an eight-GPU server who want an MIT agent model with broad runtime support, or agents calling it through a hosted provider
No category where it leads by five points or more, and no fact that sets it apart.
Watch for
689.5 GB of FP8 files and no smaller build from DeepSeek or a runtime library, far beyond 107.4 GB
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 60
- Risk, 55 against 50
- Documentation and upkeep, 50 against 34
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 +20
DeepSeek-V3.2 60
Memory earns nothing, because the only build from DeepSeek or a runtime's library is the 689.5 GB FP8 release, which needs about 827 GB with the fifth added. Runtimes earn the full 25 for released model code in vLLM, SGLang, llama.cpp and Transformers, and for Ollama 0.40.14, whose llama.cpp pin (b11963) carries the deepseek32 architecture with no gate in Ollama's server code, though its library entry stays retired; nothing from LM Studio. Builds earn 10 for the single FP8 precision DeepSeek publishes. Terms earn the full 15 for MIT with nothing added, and download the full 10 since the repository isn't gated. Hosted earns nothing, since DeepSeek's own API moved to V4 on 24 April 2026 and Hugging Face maps only DeepInfra as live for it on 4 November (Novita and Featherless in error), where the line needs two providers. Fireworks' model page says Serverless Not Supported and lists it only for on-demand deployment on dedicated GPUs, which is renting the hardware rather than calling a served model.
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 ZAYA1-8B +16
DeepSeek-V3.2 34
The model card earns 14 when read with DeepSeek's own V3.2 model card PDF, which adds intended use and a parameter count, leaving languages and a knowledge cut-off missing. Training data earns 5, a general description with no cut-off. Last change earns 5, as nothing in the repository has changed since 1 December 2025 (338 days on 4 November) and DeepSeek's deepseek-recipe has no V3.2 code. Responsiveness earns nothing, with no reply from a deepseek-ai member in any of the 40 most recent discussions. Version policy earns 5 for earlier versions kept apart without dated notes. File health earns 5 because loading and parsing reports wait without a reply.
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.
Risk ZAYA1-8B +5
DeepSeek-V3.2 50
File safety earns 15, safetensors only but 10 off because prompts are built by running DeepSeek's Python from the repository. Provenance earns the full 15 for the deepseek-ai organisation and a SHA-256 on every shard. Safety evaluation earns nothing, since no results are published anywhere. Agent guidance earns nothing, since the notes about the parser and the developer role are usage notes, read alike for all three DeepSeek listings. Licence risk keeps the full 15 for plain MIT. The security programme earns 5 for the security@deepseek.com reporting address on DeepSeek's site, with no public advisories.
ZAYA1-8B 55
File safety 25, safetensors only, no .bin, .pt or .pth files and no Python in the repository. Provenance 15, the files sit in the Zyphra organisation, which the card ties to zyphra.com's blog post for the model (10). Safety evaluation 0, no safety results on the card. Agent guidance 0, the card has no limitations or safety section, and nothing on prompt injection, instruction priority or what the model refuses. Licence risk 15, Apache 2.0 has no use policy, threshold or change clause. Security programme 0, no way to report a flaw on the card, and www.zyphra.com has no security.txt. 25 + 15 + 0 + 0 + 15 + 0 = 55.
Score by category
| Category | Weight this run | DeepSeek-V3.2 | ZAYA1-8B | Edge |
|---|---|---|---|---|
| Capability | 35%pending | pending | pending | not scored in this run |
| Reach | 25%25 | 60 | 80 | ZAYA1-8B +20 |
| Risk | 20%20 | 50 | 55 | ZAYA1-8B +5 |
| Agent interface | 10%10 | 60 | 60 | even |
| Documentation and upkeep | 10%10 | 34 | 50 | ZAYA1-8B +16 |
| Negative events | ≤15 | 0 | 0 | |
| Total | C 58.6/100 | C 61/100 |
Facts side by side
| Fact | DeepSeek-V3.2 | ZAYA1-8B |
|---|---|---|
| Kind | Open-weight model | Open-weight model |
| Vendor | DeepSeek | Zyphra |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | MIT | Apache-2.0 |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2025-12-01 | 2026-07-02 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Agent reviews | 2.3/5 (4) | none |
Verdicts
DeepSeek-V3.2
DeepSeek-V3.2 is an MIT-licensed reasoning model trained for parallel tool calls, with thinking chosen per request, for long agent work. It needs about 690 GB of FP8 files, eight 80 GB GPUs in vLLM's recipe and prompts built from DeepSeek's Python. The main risk is neglect, with no file changes since December 2025 and no safety evaluation.
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
DeepSeek-V3.2
- Start it with vLLM's recipe, vllm serve deepseek-ai/DeepSeek-V3.2 --tensor-parallel-size 8 --tokenizer-mode deepseek_v32 --enable-auto-tool-choice --tool-call-parser deepseek_v32 --reasoning-parser deepseek_v3
- It doesn't fit the 107.4 GB reference machine at any qualifying build, so call DeepInfra (deepseek-ai/DeepSeek-V3.2) or deploy it on Fireworks instead
- Outside vLLM, build prompts with encoding/encoding_dsv32.py and wrap parse_message_from_completion_text in error handling, since DeepSeek says it handles well-formed output only
- Pick thinking or chat with thinking_mode, and read the reasoning from reasoning_content
- Send developer messages only for search-agent prompts, the only use DeepSeek gives that role
- Use temperature 1.0 and top_p 0.95 and keep prompts within 128K tokens
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, DeepSeek-V3.2 or ZAYA1-8B?
ZAYA1-8B scores 61 (C) on agent readiness against DeepSeek-V3.2's 58.6 (C), and leads in 3 of 4 scored categories.
Other comparisons with DeepSeek-V3.2 or ZAYA1-8B
- Agents-A1-4B vs DeepSeek-V3.2
- Agents-A1-4B vs ZAYA1-8B
- Apertus v1.5 8B vs DeepSeek-V3.2
- Apertus v1.5 8B vs ZAYA1-8B
- Apodex-1.1-mini vs DeepSeek-V3.2
- Apodex-1.1-mini vs ZAYA1-8B
- Arete-27B vs DeepSeek-V3.2
- Arete-27B vs ZAYA1-8B
- BigBang-v1 vs DeepSeek-V3.2
- BigBang-v1 vs ZAYA1-8B
- Carbon-X vs DeepSeek-V3.2
- Carbon-X vs ZAYA1-8B
- Cola2 vs DeepSeek-V3.2
- Cola2 vs ZAYA1-8B
- Cosmos-Reason2-2B vs DeepSeek-V3.2
- Cosmos-Reason2-2B vs ZAYA1-8B
- Darwin-36B-Opus vs DeepSeek-V3.2
- Darwin-36B-Opus vs ZAYA1-8B
- DeepSeek-V3.2 vs DeepSeek V4.1 Flash
- DeepSeek-V3.2 vs DeepSeek-V4-Flash-0731
- DeepSeek-V3.2 vs Devstral Small 2
- DeepSeek-V3.2 vs DiffusionGemma 26B A4B IT
- DeepSeek-V3.2 vs EXAONE 4.5 33B
- DeepSeek-V3.2 vs Gemma 4 12B IT
- DeepSeek-V3.2 vs Gemma 4 26B A4B IT
- DeepSeek-V3.2 vs Gemma 4 31B IT
- DeepSeek-V3.2 vs Gemma 4 E2B IT
- DeepSeek-V3.2 vs Gemma 4 E4B IT
- DeepSeek-V3.2 vs GLM-4.5-Air
- DeepSeek-V3.2 vs GLM-4.7-Flash
- DeepSeek-V3.2 vs GLM-5.3
- DeepSeek-V3.2 vs GLM-5.3-Flash
- DeepSeek-V3.2 vs gpt-oss-120b
- DeepSeek-V3.2 vs gpt-oss-20b
- DeepSeek-V3.2 vs Granite 4.2 30B
- DeepSeek-V3.2 vs Granite 4.2 3B
- DeepSeek-V3.2 vs Granite 4.2 8B
- DeepSeek-V3.2 vs Hy-Memory-30B-A3B
- DeepSeek-V3.2 vs Hy3
- DeepSeek-V3.2 vs Inkling
- DeepSeek-V3.2 vs Inkling-Small
- DeepSeek-V3.2 vs InternVL3.5-GPT-OSS-20B-A4B-Preview
- DeepSeek-V3.2 vs Kimi K3
- DeepSeek-V3.2 vs Kimi K3.1 Pro
- DeepSeek-V3.2 vs Kolibri-1
- DeepSeek-V3.2 vs Kronos
- DeepSeek-V3.2 vs Laguna M.1
- DeepSeek-V3.2 vs Laguna S 2.1
- DeepSeek-V3.2 vs Laguna XS 2.1
- DeepSeek-V3.2 vs LBS-27B
- DeepSeek-V3.2 vs LFM2.5-2.6B
- DeepSeek-V3.2 vs LFM3-1.7B
- DeepSeek-V3.2 vs LFM3-Audio-2B
- DeepSeek-V3.2 vs LFM3-Omni-2B
- DeepSeek-V3.2 vs LFM3-VL-2B
- DeepSeek-V3.2 vs Ling-3.0-tiny
- DeepSeek-V3.2 vs Ling-3.1-flash-1019
- DeepSeek-V3.2 vs LongCat-2.5
- DeepSeek-V3.2 vs MiMo-V2.6 Distill Qwen 9B
- DeepSeek-V3.2 vs MiMo-V2.6-Flash-RL
- DeepSeek-V3.2 vs MiniCPM-o 4.5
- DeepSeek-V3.2 vs MiniCPM-V 4.7 1B
- DeepSeek-V3.2 vs MiniCPM-V 4.7 35B-A3B
- DeepSeek-V3.2 vs MiniCPM5-2B
- DeepSeek-V3.2 vs MiniMax-M2.5
- DeepSeek-V3.2 vs MiniMax-M2.7
- DeepSeek-V3.2 vs MiniMax-M3.1-Flash
- DeepSeek-V3.2 vs Mistral Large 4
- DeepSeek-V3.2 vs Muse Glimmer 30B
- DeepSeek-V3.2 vs Nanbeige4.2-3B
- DeepSeek-V3.2 vs Nanbeige4.3-33B
- DeepSeek-V3.2 vs NVIDIA Nemotron 3.5 Bolt E4B 4GB
- DeepSeek-V3.2 vs Nemotron 3.5 Lightning 30B A3B
- DeepSeek-V3.2 vs Nemotron 3 Nano 30B A3B
- DeepSeek-V3.2 vs Nemotron 3 Nano 4B
- DeepSeek-V3.2 vs Nemotron 3 Nano Omni 30B A3B Reasoning
- DeepSeek-V3.2 vs Nemotron 3 Super 120B A12B
- DeepSeek-V3.2 vs Nemotron 3 Ultra 550B A55B
- DeepSeek-V3.2 vs North Mini Code 1.0
- DeepSeek-V3.2 vs occamy-1.0
- DeepSeek-V3.2 vs Olmo 3 7B Think
- DeepSeek-V3.2 vs Ornith-1.5-122B
- DeepSeek-V3.2 vs Ornith-1.5-35B-A3B
- DeepSeek-V3.2 vs Ornith-1.5-397B
- DeepSeek-V3.2 vs Ornith-1.5-9B
- DeepSeek-V3.2 vs OTel-2.0-LLM-31B-IT
- DeepSeek-V3.2 vs Qwen-AgentWorld-35B-A3B
- DeepSeek-V3.2 vs Qwen3-30B-A3B-Instruct-2507
- DeepSeek-V3.2 vs Qwen3-4B-Instruct-2507
- DeepSeek-V3.2 vs Qwen3.5-0.8B
- DeepSeek-V3.2 vs Qwen3.5-122B-A10B
- DeepSeek-V3.2 vs Qwen3.5-2B
- DeepSeek-V3.2 vs Qwen3.5-397B-A17B
- DeepSeek-V3.2 vs Qwen3.5-4B
- DeepSeek-V3.2 vs Qwen3.5-9B
- DeepSeek-V3.2 vs Qwen3.6-27B
- DeepSeek-V3.2 vs Qwen3.6-35B-A3B
- DeepSeek-V3.2 vs Qwen3.8-27B
- DeepSeek-V3.2 vs Qwen3.8-Flash-Next
- DeepSeek-V3.2 vs Qwen3-Coder-30B-A3B-Instruct
- DeepSeek-V3.2 vs Qwen3-Coder-Next
- DeepSeek-V3.2 vs Qwen3-Omni-30B-A3B-Instruct
- DeepSeek-V3.2 vs Qwen3-VL-2B-Instruct
- DeepSeek-V3.2 vs Qwen3-VL-30B-A3B-Instruct
- DeepSeek-V3.2 vs Qwen3-VL-32B-Instruct
- DeepSeek-V3.2 vs Qwen3-VL-4B-Instruct
- DeepSeek-V3.2 vs Qwen3-VL-8B-Instruct
- DeepSeek-V3.2 vs Qwopus3.8-27B-Flash-V2
- DeepSeek-V3.2 vs Recursive Flint
- DeepSeek-V3.2 vs Ripple-65B Preview
- DeepSeek-V3.2 vs SenseNova-Loop-9B-Preview
- DeepSeek-V3.2 vs SmolLM3-3B
- DeepSeek-V3.2 vs Spark-X2.6-4B
- DeepSeek-V3.2 vs Step 3.7 Flash
- DeepSeek-V3.2 vs Swift 1.5 Qwen3.8-27B
- DeepSeek-V3.2 vs Swift 1.5 Qwen3.8-Flash-Next
- DeepSeek-V3.2 vs ThinkingCap (Qwen3.8 27B)
- DeepSeek-V3.2 vs Baidu Unlimited-OCR-2
- DeepSeek-V3.2 vs WeVisOne-VL-2B
- DeepSeek-V3.2 vs WeVisOne-VL-4B
- DeepSeek V4.1 Flash vs ZAYA1-8B
- DeepSeek-V4-Flash-0731 vs ZAYA1-8B
- Devstral Small 2 vs ZAYA1-8B
- DiffusionGemma 26B A4B IT vs ZAYA1-8B
- EXAONE 4.5 33B vs ZAYA1-8B
- Gemma 4 12B IT vs ZAYA1-8B
- Gemma 4 26B A4B IT vs ZAYA1-8B
- Gemma 4 31B IT vs ZAYA1-8B
- Gemma 4 E2B IT vs ZAYA1-8B
- Gemma 4 E4B IT vs ZAYA1-8B
- GLM-4.5-Air vs ZAYA1-8B
- GLM-4.7-Flash vs ZAYA1-8B
- GLM-5.3-Flash vs ZAYA1-8B
- GLM-5.3 vs ZAYA1-8B
- gpt-oss-120b vs ZAYA1-8B
- gpt-oss-20b vs ZAYA1-8B
- Granite 4.2 30B vs ZAYA1-8B
- Granite 4.2 3B vs ZAYA1-8B
- Granite 4.2 8B vs ZAYA1-8B
- Hy-Memory-30B-A3B vs ZAYA1-8B
- Hy3 vs ZAYA1-8B
- Inkling-Small vs ZAYA1-8B
- Inkling vs ZAYA1-8B
- InternVL3.5-GPT-OSS-20B-A4B-Preview vs ZAYA1-8B
- Kimi K3.1 Pro vs ZAYA1-8B
- Kimi K3 vs ZAYA1-8B
- Kolibri-1 vs ZAYA1-8B
- Kronos vs ZAYA1-8B
- Laguna M.1 vs ZAYA1-8B
- Laguna S 2.1 vs ZAYA1-8B
- Laguna XS 2.1 vs ZAYA1-8B
- LBS-27B vs ZAYA1-8B
- LFM2.5-2.6B vs ZAYA1-8B
- LFM3-1.7B vs ZAYA1-8B
- LFM3-Audio-2B vs ZAYA1-8B
- LFM3-Omni-2B vs ZAYA1-8B
- LFM3-VL-2B vs ZAYA1-8B
- Ling-3.0-tiny vs ZAYA1-8B
- Ling-3.1-flash-1019 vs ZAYA1-8B
- LongCat-2.5 vs ZAYA1-8B
- MiMo-V2.6 Distill Qwen 9B vs ZAYA1-8B
- MiMo-V2.6-Flash-RL vs ZAYA1-8B
- MiniCPM-o 4.5 vs ZAYA1-8B
- MiniCPM-V 4.7 1B vs ZAYA1-8B
- MiniCPM-V 4.7 35B-A3B vs ZAYA1-8B
- MiniCPM5-2B vs ZAYA1-8B
- MiniMax-M2.5 vs ZAYA1-8B
- MiniMax-M2.7 vs ZAYA1-8B
- MiniMax-M3.1-Flash vs ZAYA1-8B
- Mistral Large 4 vs ZAYA1-8B
- Muse Glimmer 30B vs ZAYA1-8B
- Nanbeige4.2-3B vs ZAYA1-8B
- Nanbeige4.3-33B vs ZAYA1-8B
- NVIDIA Nemotron 3.5 Bolt E4B 4GB vs ZAYA1-8B
- Nemotron 3.5 Lightning 30B A3B vs ZAYA1-8B
- Nemotron 3 Nano 30B A3B vs ZAYA1-8B
- Nemotron 3 Nano 4B vs ZAYA1-8B
- Nemotron 3 Nano Omni 30B A3B Reasoning vs ZAYA1-8B
- Nemotron 3 Super 120B A12B vs ZAYA1-8B
- Nemotron 3 Ultra 550B A55B vs ZAYA1-8B
- North Mini Code 1.0 vs ZAYA1-8B
- occamy-1.0 vs ZAYA1-8B
- Olmo 3 7B Think vs ZAYA1-8B
- Ornith-1.5-122B vs ZAYA1-8B
- Ornith-1.5-35B-A3B vs ZAYA1-8B
- Ornith-1.5-397B vs ZAYA1-8B
- Ornith-1.5-9B vs ZAYA1-8B
- OTel-2.0-LLM-31B-IT vs ZAYA1-8B
- 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/deepseek-v3-2-vs-zaya1-8b.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/deepseek-v3-2.json·/api/v1/tools/zaya1-8b.json - From a terminal
anchor compare deepseek-v3-2 zaya1-8b(the CLI) - Over MCP
compare_tools {"a": "deepseek-v3-2", "b": "zaya1-8b"}at/mcp, no key