Sign in

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

Nanbeige4.3-33B vs Ornith-1.5-122B

Ornith-1.5-122B and Nanbeige4.3-33B score within a point of each other on agent readiness, 61 (C) and 60.8 (C). Nanbeige4.3-33B leads on reach, risk and 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

Nanbeige4.3-33BNanbeige LLM Lab (BOSS Zhipin) · Open-weight model C60.8/100#86 of 160 open-weight models Ornith-1.5-122BOrnith · Open-weight model C61/100#81 of 160 open-weight models

Which one, for what

Nanbeige4.3-33B C

Best for Agents with a 32 GB GPU (INT4) or more, or the 128 GB reference machine at BF16, that want an Apache-tagged 33B model for long coding and tool loops.

Ahead on

  • Reach, 80 against 75
  • Risk, 60 against 50
  • Documentation and upkeep, 56 against 36

Watch for

Independent results so far are Artificial Analysis's alone (Intelligence Index v5.0 20.4, Terminal-Bench 4.0 29.8 per cent); the card's other agentic numbers are Nanbeige's own runs

Ornith-1.5-122B C

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

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

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.

Documentation and upkeep Nanbeige4.3-33B +20

Nanbeige4.3-33B 56

The model card earns 11, with intended use, parameters, context and languages but no limitations, architecture or cut-off. Training data earns 0, as nothing describes it. Last change earns 20 for the quantised builds of 31 October 2026. Responsiveness earns 10, a Nanbeige member answering nine of 30 discussions. Version policy earns 5 for a first release, with a config change made and reverted under bare commit titles. File health earns 10, the files and the card agreeing.

Ornith-1.5-122B 36

Model card 11, it covers intended use, architecture, parameters and context but not limitations, languages or a knowledge cut-off. Training data 5, a description of the method with no data or cut-off. Last change 20, a folder upload to the MLX builds on 24 October 2026, 17 days ago. Responsiveness 0, Ornith answered none of the 5 questions and reports. Version policy 0, the MLX builds were uploaded a second time four days after the first with no note. File health 0, the card links a missing LICENSE, states hardware its own files don't fit and names a variant that doesn't exist, and the two chat templates differ. 11 + 5 + 20 + 0 + 0 + 0 = 36.

Risk Nanbeige4.3-33B +10

Nanbeige4.3-33B 60

File safety earns 25, safetensors only and no repository code, so the card's trust_remote_code has nothing to run. Provenance earns 15, the lab's own organisation as its arXiv report links it, with a hash for every file. Safety evaluation earns 0 and agent guidance 0, since neither card says anything on either. Licence risk keeps all 15 under Apache 2.0. The security programme earns 5 for BOSS Zhipin's security response centre, which isn't linked to the model.

Ornith-1.5-122B 50

File safety 25, safetensors and GGUF only and no Python in any of Ornith's repositories for this size, so the card's --trust-remote-code flag loads nothing from the repository. Provenance 15, the files come from the ornith-ai organisation Ornith's blog links to, with a SHA-256 for every weight file. Safety evaluation 0 and agent guidance 0, nothing published on either. Licence risk 10, MIT carries no policy, threshold or changeable terms, but the card's licence link is broken. Security programme 0, no security.txt, disclosure policy or security contact.

Reach Nanbeige4.3-33B +5

Nanbeige4.3-33B 80

Memory earns 20, since Nanbeige's INT4 build is 22.57 GB, about 27 GB with a fifth added, which fits 32 GB. Runtimes earn 20 from released vLLM, SGLang, Transformers and llama.cpp, which all run the Llama architecture, and Ollama and LM Studio have no build. Builds earn 15 for Nanbeige's INT4, INT8 and FP8 builds of 31 October 2026. Terms earn 15 for Apache 2.0 with nothing added, though only the metadata names it. Download earns 10, with no gate. Hosted earns 0, as no provider or Nanbeige API serves it.

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

CategoryWeight this runNanbeige4.3-33BOrnith-1.5-122BEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%258075Nanbeige4.3-33B +5
Risk20%206050Nanbeige4.3-33B +10
Agent interface10%108585even
Documentation and upkeep10%105636Nanbeige4.3-33B +20
Negative events≤1500
TotalC 60.8/100C 61/100

Facts side by side

FactNanbeige4.3-33BOrnith-1.5-122B
KindOpen-weight modelOpen-weight model
VendorNanbeige LLM Lab (BOSS Zhipin)Ornith
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0 (Hub metadata only; the repository has no LICENSE file)MIT
Read-only variant documentednono
llms.txtnono
Last release2026-10-312026-10-24
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked

How the scores have moved

Nanbeige4.3-33B

Ornith-1.5-122B

No score change since it was listed.

Verdicts

Nanbeige4.3-33B

A dense 33B Llama-architecture cousin for long agentic coding and office tasks, with per-request thinking, XML tool calls that stock vLLM and SGLang parse, and 512K of context. Nanbeige's INT4 build needs about 27 GB. Artificial Analysis's first independent runs give it 20.4 on its Intelligence Index, and there are no safety results, training data notes or licence file.

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

Nanbeige4.3-33B

  1. Serve with vllm serve Nanbeige/Nanbeige4.3-33B --enable-auto-tool-choice --reasoning-parser qwen3 --tool-call-parser qwen3_coder, as the card says, or SGLang with the same two parsers
  2. On a 32 GB GPU use Nanbeige/Nanbeige4.3-33B-INT4 with the same vLLM or SGLang flags; the INT8 and FP8 builds need about 43 GB
  3. Keep tool_call_format at its default xml, since qwen3_coder parses that format; the json option writes Hermes-style JSON calls, which need a different parser such as vLLM's hermes
  4. Pass chat_template_kwargs {"preserve_thinking": true} for multi-turn tool use and coding, and {"enable_thinking": false} to skip reasoning, as the card recommends
  5. Use temperature 1.0, top_p 0.95 and up to 65,536 new tokens for agent work, and temperature 0.6 for reasoning and chat, per the card
  6. Send your own system prompt, since without one the template injects a Chinese identity line, or a Chinese tool-expert prompt when tools are passed
  7. Send one system message at the start only, as the template raises an error for a later one
  8. In plain Transformers pass use_cache=True to generate, since config.json and generation_config.json set it false; trust_remote_code isn't needed

Ornith-1.5-122B

  1. Start it with ollama run ornith-1.5:122b-q4_K_M, or llama-server -hf ornith-ai/Ornith-1.5-122B-GGUF:Q4_K_M --jinja -c 262144
  2. 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
  3. 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
  4. Thinking is on by default. Send chat_template_kwargs with enable_thinking false for short tasks, a switch the card doesn't mention
  5. Pin which template your runtime loads, since chat_template.jinja keeps earlier reasoning and the tokenizer_config.json template drops it
  6. Use temperature 0.6, top_p 0.95, top_k 20 for coding and temperature 1.0 for general tasks, as the card recommends
  7. 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, Nanbeige4.3-33B or Ornith-1.5-122B?

Ornith-1.5-122B and Nanbeige4.3-33B score within a point of each other on agent readiness, 61 (C) and 60.8 (C). Nanbeige4.3-33B leads on reach, risk and documentation and upkeep.

Other comparisons with Nanbeige4.3-33B or Ornith-1.5-122B

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