Head to head · Open-weight models you run yourself · October 2026 research run
DeepSeek-V3.2 vs Ornith-1.5-122B
Ornith-1.5-122B 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 4969 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
Best for Local coding and terminal agents on a 128 GB unified-memory machine or a 96 GB GPU setup, where a clear licence file and an answering publisher aren't required
Ahead on
- Reach, 75 against 60
- Agent interface, 85 against 60
Watch for
No LICENSE file though the card links one, and no notice for the Apache 2.0 Qwen3.5 and Gemma 4 work it builds on
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.
Agent interface Ornith-1.5-122B +25
DeepSeek-V3.2 60
The chat template earns 10, as the format exists only as Python code to run. The tool-calling format earns 10 because DeepSeek documents the DSML format in code but names no runtime parser, which only vLLM's own recipe does. Trained tool calling earns the full 20 for several calls in one block. Structured output earns nothing, as JSON output isn't documented. Reasoning control earns 10 for thinking or chat mode per request with reasoning_content returned. Context earns 10 for 128K trained tokens.
Ornith-1.5-122B 85
Chat template 20, a Jinja file in the repository. Tool-calling format 25, the card shows how tools go in and how calls come back and names the parser for vLLM and SGLang. Trained tool calling 20, Ornith trains it on agent tasks and the template renders several calls in one turn. Structured output 0, not documented or claimed. Reasoning control 10, Ornith's template reads enable_thinking per request and the card says the reasoning comes back in reasoning_content, though the card doesn't name the switch. Context 10, 262,144 tokens native.
Reach Ornith-1.5-122B +15
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.
Ornith-1.5-122B 75
Memory 10, since Ornith's own MLX 4-bit build is 69.7 GB and needs about 83.6 GB with the fifth added, over 64 GB and inside the reference machine's 107.4 GB, as do its Q4_K_M GGUF, its NVFP4 build and Ollama's build. Runtimes 25, the most the line gives, from vLLM 0.33.0, SGLang 0.5.23, Transformers 5.22.2, llama.cpp's qwen35moe architecture, Ollama's library and LM Studio's catalogue for the qwen35moe architecture. Builds 15, Ornith publishes FP8, NVFP4, GGUF and MLX at several precisions. Terms 15, MIT as named in the card's metadata, with nothing added, read by its terms though the repository has no licence file. Download 10, nothing is gated. Hosted 0, Ornith runs no API and no inference provider serves it. 10 + 25 + 15 + 15 + 10 + 0 = 75.
Score by category
| Category | Weight this run | DeepSeek-V3.2 | Ornith-1.5-122B | Edge |
|---|---|---|---|---|
| Capability | 35%pending | pending | pending | not scored in this run |
| Reach | 25%25 | 60 | 75 | Ornith-1.5-122B +15 |
| Risk | 20%20 | 50 | 50 | even |
| Agent interface | 10%10 | 60 | 85 | Ornith-1.5-122B +25 |
| Documentation and upkeep | 10%10 | 34 | 36 | Ornith-1.5-122B +2 |
| Negative events | ≤15 | 0 | 0 | |
| Total | C 58.6/100 | C 61/100 |
Facts side by side
| Fact | DeepSeek-V3.2 | Ornith-1.5-122B |
|---|---|---|
| Kind | Open-weight model | Open-weight model |
| Vendor | DeepSeek | Ornith |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | MIT | MIT |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2025-12-01 | 2026-10-24 |
| 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.
Ornith-1.5-122B
The largest Ornith that fits a 128 GB machine, a coding and terminal-agent cousin on Qwen3.5-122B-A10B's architecture with XML tool calls and 262,144 tokens of context. Its 4-bit builds need 84 to 93 GB. The main risk is an absent publisher, with no licence file, safety results or replies, and a card that misstates the hardware.
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
Ornith-1.5-122B
- Start it with
ollama run ornith-1.5:122b-q4_K_M, orllama-server -hf ornith-ai/Ornith-1.5-122B-GGUF:Q4_K_M --jinja -c 262144 - Budget about 92 GB for the Q4_K_M GGUF with a working context, and less context if the machine has under 100 GB for the model
- In vLLM pass
--enable-auto-tool-choice --tool-call-parser qwen3_xml --reasoning-parser qwen3, and in SGLang--tool-call-parser qwen3_coder --reasoning-parser qwen3, so tool calls and reasoning come back parsed - Thinking is on by default. Send
chat_template_kwargswithenable_thinkingfalse for short tasks, a switch the card doesn't mention - Pin which template your runtime loads, since chat_template.jinja keeps earlier reasoning and the tokenizer_config.json template drops it
- Use temperature 0.6, top_p 0.95, top_k 20 for coding and temperature 1.0 for general tasks, as the card recommends
- Add mmproj-Ornith-1.5-122B-BF16.gguf (0.9 GB) for image input in llama.cpp, and validate JSON output yourself, since structured output isn't documented
Questions
Which is better for AI agents, DeepSeek-V3.2 or Ornith-1.5-122B?
Ornith-1.5-122B 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 Ornith-1.5-122B
- Agents-A1-4B vs DeepSeek-V3.2
- Agents-A1-4B vs Ornith-1.5-122B
- Apertus v1.5 8B vs DeepSeek-V3.2
- Apertus v1.5 8B vs Ornith-1.5-122B
- Apodex-1.1-mini vs DeepSeek-V3.2
- Apodex-1.1-mini vs Ornith-1.5-122B
- Arete-27B vs DeepSeek-V3.2
- Arete-27B vs Ornith-1.5-122B
- BigBang-v1 vs DeepSeek-V3.2
- BigBang-v1 vs Ornith-1.5-122B
- Carbon-X vs DeepSeek-V3.2
- Carbon-X vs Ornith-1.5-122B
- Cosmos-Reason2-2B vs DeepSeek-V3.2
- Cosmos-Reason2-2B vs Ornith-1.5-122B
- Darwin-36B-Opus vs DeepSeek-V3.2
- Darwin-36B-Opus vs Ornith-1.5-122B
- DeepSeek-V3.2 vs DeepSeek V4.1 Flash
- DeepSeek-V3.2 vs DeepSeek-V4-Flash-0731
- DeepSeek-V3.2 vs DiffusionGemma 26B A4B IT
- 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 MiMo-V2.6 Distill Qwen 9B
- 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 Nanbeige4.3-33B
- 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 occamy-1.0
- DeepSeek-V3.2 vs Olmo 3 7B Think
- 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 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 SmolLM3-3B
- DeepSeek-V3.2 vs Spark-X2.6-4B
- 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 V4.1 Flash vs Ornith-1.5-122B
- DeepSeek-V4-Flash-0731 vs Ornith-1.5-122B
- DiffusionGemma 26B A4B IT vs Ornith-1.5-122B
- Gemma 4 12B IT vs Ornith-1.5-122B
- Gemma 4 26B A4B IT vs Ornith-1.5-122B
- Gemma 4 31B IT vs Ornith-1.5-122B
- Gemma 4 E2B IT vs Ornith-1.5-122B
- Gemma 4 E4B IT vs Ornith-1.5-122B
- GLM-4.5-Air vs Ornith-1.5-122B
- GLM-4.7-Flash vs Ornith-1.5-122B
- GLM-5.3-Flash vs Ornith-1.5-122B
- GLM-5.3 vs Ornith-1.5-122B
- gpt-oss-120b vs Ornith-1.5-122B
- gpt-oss-20b vs Ornith-1.5-122B
- Granite 4.2 30B vs Ornith-1.5-122B
- Granite 4.2 3B vs Ornith-1.5-122B
- Granite 4.2 8B vs Ornith-1.5-122B
- Hy-Memory-30B-A3B vs Ornith-1.5-122B
- Hy3 vs Ornith-1.5-122B
- Inkling-Small vs Ornith-1.5-122B
- Inkling vs Ornith-1.5-122B
- InternVL3.5-GPT-OSS-20B-A4B-Preview vs Ornith-1.5-122B
- Kimi K3.1 Pro vs Ornith-1.5-122B
- Kimi K3 vs Ornith-1.5-122B
- Kolibri-1 vs Ornith-1.5-122B
- Kronos vs Ornith-1.5-122B
- Laguna M.1 vs Ornith-1.5-122B
- Laguna S 2.1 vs Ornith-1.5-122B
- Laguna XS 2.1 vs Ornith-1.5-122B
- LBS-27B vs Ornith-1.5-122B
- LFM2.5-2.6B vs Ornith-1.5-122B
- LFM3-1.7B vs Ornith-1.5-122B
- LFM3-Audio-2B vs Ornith-1.5-122B
- LFM3-Omni-2B vs Ornith-1.5-122B
- LFM3-VL-2B vs Ornith-1.5-122B
- Ling-3.0-tiny vs Ornith-1.5-122B
- Ling-3.1-flash-1019 vs Ornith-1.5-122B
- MiMo-V2.6 Distill Qwen 9B vs Ornith-1.5-122B
- MiniCPM-o 4.5 vs Ornith-1.5-122B
- MiniCPM-V 4.7 1B vs Ornith-1.5-122B
- MiniCPM-V 4.7 35B-A3B vs Ornith-1.5-122B
- MiniCPM5-2B vs Ornith-1.5-122B
- MiniMax-M2.5 vs Ornith-1.5-122B
- MiniMax-M2.7 vs Ornith-1.5-122B
- MiniMax-M3.1-Flash vs Ornith-1.5-122B
- Mistral Large 4 vs Ornith-1.5-122B
- Muse Glimmer 30B vs Ornith-1.5-122B
- Nanbeige4.3-33B vs Ornith-1.5-122B
- NVIDIA Nemotron 3.5 Bolt E4B 4GB vs Ornith-1.5-122B
- Nemotron 3.5 Lightning 30B A3B vs Ornith-1.5-122B
- Nemotron 3 Nano 30B A3B vs Ornith-1.5-122B
- Nemotron 3 Nano 4B vs Ornith-1.5-122B
- Nemotron 3 Nano Omni 30B A3B Reasoning vs Ornith-1.5-122B
- Nemotron 3 Super 120B A12B vs Ornith-1.5-122B
- Nemotron 3 Ultra 550B A55B vs Ornith-1.5-122B
- occamy-1.0 vs Ornith-1.5-122B
- Olmo 3 7B Think vs Ornith-1.5-122B
- Ornith-1.5-122B vs Ornith-1.5-35B-A3B
- Ornith-1.5-122B vs Ornith-1.5-397B
- Ornith-1.5-122B vs Ornith-1.5-9B
- Ornith-1.5-122B vs Qwen-AgentWorld-35B-A3B
- Ornith-1.5-122B vs Qwen3-30B-A3B-Instruct-2507
- Ornith-1.5-122B vs Qwen3-4B-Instruct-2507
- Ornith-1.5-122B vs Qwen3.5-0.8B
- Ornith-1.5-122B vs Qwen3.5-122B-A10B
- Ornith-1.5-122B vs Qwen3.5-2B
- Ornith-1.5-122B vs Qwen3.5-397B-A17B
- Ornith-1.5-122B vs Qwen3.5-4B
- Ornith-1.5-122B vs Qwen3.5-9B
- Ornith-1.5-122B vs Qwen3.6-27B
- Ornith-1.5-122B vs Qwen3.6-35B-A3B
- Ornith-1.5-122B vs Qwen3.8-27B
- Ornith-1.5-122B vs Qwen3.8-Flash-Next
- Ornith-1.5-122B vs Qwen3-Coder-30B-A3B-Instruct
- Ornith-1.5-122B vs Qwen3-Coder-Next
- Ornith-1.5-122B vs Qwen3-Omni-30B-A3B-Instruct
- Ornith-1.5-122B vs Qwen3-VL-2B-Instruct
- Ornith-1.5-122B vs Qwen3-VL-30B-A3B-Instruct
- Ornith-1.5-122B vs Qwen3-VL-32B-Instruct
- Ornith-1.5-122B vs Qwen3-VL-4B-Instruct
- Ornith-1.5-122B vs Qwen3-VL-8B-Instruct
- Ornith-1.5-122B vs Qwopus3.8-27B-Flash-V2
- Ornith-1.5-122B vs Recursive Flint
- Ornith-1.5-122B vs Ripple-65B Preview
- Ornith-1.5-122B vs SmolLM3-3B
- Ornith-1.5-122B vs Spark-X2.6-4B
- Ornith-1.5-122B vs Swift 1.5 Qwen3.8-27B
- Ornith-1.5-122B vs Swift 1.5 Qwen3.8-Flash-Next
- Ornith-1.5-122B vs ThinkingCap (Qwen3.8 27B)
- Ornith-1.5-122B vs Baidu Unlimited-OCR-2
Machine-readable
- This page as Markdown
/compare/deepseek-v3-2-vs-ornith-1-5-122b.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/deepseek-v3-2.json·/api/v1/tools/ornith-1-5-122b.json - From a terminal
anchor compare deepseek-v3-2 ornith-1-5-122b(the CLI) - Over MCP
compare_tools {"a": "deepseek-v3-2", "b": "ornith-1-5-122b"}at/mcp, no key