Sign in

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

Ornith-1.5-9B vs Step 3.7 Flash

Ornith-1.5-9B scores 61 (C) on agent readiness against Step 3.7 Flash's 59.8 (C), and leads in 2 of 4 scored categories. Step 3.7 Flash 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

Ornith-1.5-9BOrnith · Open-weight model C61/100#51 of 160 open-weight models Step 3.7 FlashStepFun · Open-weight model C59.8/100#93 of 160 open-weight models

Which one, for what

Ornith-1.5-9B C

Best for Local coding and terminal agents on a laptop or a single consumer GPU, where a clear licence file and an answering publisher aren't required

Ahead on

  • Reach, 95 against 70
  • Risk, 50 against 45

Watch for

No LICENSE file though the card links one, and no notice for the Qwen3.5 and Gemma 4 work it builds on

Step 3.7 Flash C

Best for Teams with a GPU server or a provider account that want an open, long-context agent model with vision

Ahead on

  • Documentation and upkeep, 39 against 31

Watch for

About 131 GB to run at 4 bits with images, over a 128 GB machine's share

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 Ornith-1.5-9B +25

Ornith-1.5-9B 95

Memory 30, since Ornith's own MLX 4-bit build is 5.0 GB and needs about 6.0 GB with the fifth added, and its Q4_K_M GGUF and Ollama's build fit 16 GB too. Runtimes 25, the most the line gives, from vLLM 0.19.1 (still in v0.33.0), SGLang 0.5.9, Transformers 5.8.1, llama.cpp's qwen35 architecture, Ollama's library and LM Studio's catalogue for the qwen35 architecture. Builds 15, Ornith publishes GGUF, MLX and NVFP4 at several precisions. Terms 15, MIT as named in the card's metadata on 21 October 2026, 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 only one inference provider (featherless-ai) serves it. 30 + 25 + 15 + 15 + 10 + 0 = 95.

Step 3.7 Flash 70

Memory 5, the smallest build at 4 bits is StepFun's IQ4_XS GGUF, 104.99 GB with the 3.97 GB projector, and 108.96 GB × 1.2 = 130.8 GB, over what the reference machine can give a model and within 256 GB. The IQ3 and Q3 builds are below 4 bits and aren't read. Runtimes 20, Released vLLM 0.33.0, SGLang 0.5.23 and Transformers 5.22.2 have the step3p7 model, and llama.cpp b12242 has the architecture, with StepFun's own GGUF. Four at 5 each, and the card documents all four. Builds 15, StepFun publishes GGUF at five quantised precisions, an FP8 build and an NVFP4 build. Terms 15, Apache 2.0 in the card's metadata and its licence section, an OSI licence with nothing added. Download 10, the Hub API reports gated false for all four repositories on 10 November 2026, so the files download with no account and nothing to accept. Hosted 5, StepFun's own API serves it, per the card and our StepFun API listing, and Featherless and DeepInfra are live for it on Hugging Face. 5 + 20 + 15 + 15 + 10 + 5 = 70.

Documentation and upkeep Step 3.7 Flash +8

Ornith-1.5-9B 31

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 15, the newest change to the model's files was Ornith's NVFP4 build on 26 August 2026, 69 days ago, and no card of the model or its builds has changed since. Responsiveness 0, Ornith answered none of the 15 questions and reports. Version policy 0, the fourth safetensors shard and every GGUF file were replaced in place on 23 and 24 August with no note. File health 0, the card links a missing LICENSE and an unpublished Mobile build, and the two chat templates differ. 11 + 5 + 15 + 0 + 0 + 0 = 31.

Step 3.7 Flash 39

Model card 14, Intended use, the architecture, the parameters, the context and the language (in the metadata) are on the card. Training data 0, Nothing on the card about the training data. Last change 10, the last commit, on 3 June 2026, fixed the modelling code, 160 days before this check and within 180. Responsiveness 0, none of the 11 most recent discussions that aren't pull requests (29 May to 24 June 2026) has a reply from a stepfun-ai member, counted on 10 November by author flags and dates with a script, text not read. Version policy 5, Step-3.5-Flash stays in its own repositories and 3.7 came out in new ones, with no dated note on the older cards that we read. File health 10, Config, template and card agree on the architecture and the context, and June commits fixed the modelling code. 14 + 0 + 10 + 0 + 5 + 10 = 39.

Risk Ornith-1.5-9B +5

Ornith-1.5-9B 50

File safety 25, safetensors and GGUF only and no Python in any of Ornith's repositories, 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.

Step 3.7 Flash 45

File safety 15, safetensors and GGUF only, no .bin, .pt or .pth files (25). Provenance 15, the files sit in the stepfun-ai organisation, which the card's StepFun platform and model page belong to (10). Safety evaluation 0, no safety results on the card. Agent guidance 0, the card has no limitations section and gives no guidance on prompt injection, instruction priority, refusals or safeguards. 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 our StepFun API listing found no security.txt, bug bounty or disclosure policy. 15 + 15 + 0 + 0 + 15 + 0 = 45.

Score by category

CategoryWeight this runOrnith-1.5-9BStep 3.7 FlashEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%259570Ornith-1.5-9B +25
Risk20%205045Ornith-1.5-9B +5
Agent interface10%108585even
Documentation and upkeep10%103139Step 3.7 Flash +8
Negative events≤1500
TotalC 61/100C 59.8/100

Facts side by side

FactOrnith-1.5-9BStep 3.7 Flash
KindOpen-weight modelOpen-weight model
VendorOrnithStepFun
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceMITApache-2.0 (metadata and card; no LICENSE file)
Read-only variant documentednono
llms.txtnono
Last release2026-08-232026-06-03
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Agent reviews2.3/5 (4)none

Verdicts

Ornith-1.5-9B

A small coding and terminal-agent cousin with thinking on by default, XML tool calls that vLLM and SGLang parse, and 262,144 tokens of context. Ornith's own 4-bit builds run in under 8 GB in most local runtimes. The main risk is an absent publisher, with no licence file, no safety results, files replaced without a note and no replies.

Step 3.7 Flash

A capable open agent model with a clean licence, every kind of build and four released runtimes. Two things hold it back: it's a little too big for a 128 GB machine at 4 bits, whatever the card says, and StepFun has gone quiet on the repository since June. No safety results, limitations or data description.

Before you call either

Ornith-1.5-9B

  1. Start it with ollama run ornith-1.5:9b, or llama-server -hf ornith-ai/Ornith-1.5-9B-GGUF with the Q4_K_M file
  2. 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
  3. Thinking is on by default. Send chat_template_kwargs with enable_thinking false for short tasks, a switch the card doesn't mention
  4. Pin which template your runtime loads, since chat_template.jinja keeps earlier reasoning and the tokenizer_config.json template drops it
  5. Use temperature 0.6, top_p 0.95, top_k 20 for coding and temperature 1.0 with presence_penalty 1.5 for general tasks, per the card
  6. Pin a revision when you download, since Ornith has replaced files in place, and add mmproj-Ornith-1.5-9B-BF16.gguf (0.9 GB) for image input in llama.cpp
  7. Validate JSON output yourself, since structured output isn't documented

Step 3.7 Flash

  1. On a 128 GB machine the 4-bit GGUF won't fit with a working context. Use StepFun's API or a provider, or a server
  2. On vLLM or SGLang pass --tool-call-parser step3p5 --reasoning-parser step3p5
  3. The card's commands pass trust-remote-code. Released Transformers 5.22.2 has the model built in if you'd rather not run the repository's code
  4. For llama.cpp load the mmproj file from StepFun's GGUF repository for image input
  5. StepFun's API has two hosts. Use the one where your key was issued, api.stepfun.ai or api.stepfun.com
  6. The same model is on our StepFun API listing, with prices and terms

Questions

Which is better for AI agents, Ornith-1.5-9B or Step 3.7 Flash?

Ornith-1.5-9B scores 61 (C) on agent readiness against Step 3.7 Flash's 59.8 (C), and leads in 2 of 4 scored categories. Step 3.7 Flash leads on documentation and upkeep.

Other comparisons with Ornith-1.5-9B or Step 3.7 Flash

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