Sign in

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

Qwen3.5-2B vs Step 3.7 Flash

Step 3.7 Flash scores 59.8 (C) on agent readiness against Qwen3.5-2B's 50.5 (D), and leads in 2 of 4 scored categories. Qwen3.5-2B leads on reach and risk. 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

Qwen3.5-2BAlibaba (Qwen team) · Open-weight model D50.5/100#144 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

Qwen3.5-2B D

Best for Builders who want a cheap local helper or fine-tuning base for narrow tasks and image reading on a laptop, small GPU or CPU

Ahead on

  • Reach, 80 against 70
  • Risk, 55 against 45

Watch for

No quantised build from Alibaba, and only one inference provider

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

  • Agent interface, 85 against 60

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.

Agent interface Step 3.7 Flash +25

Qwen3.5-2B 60

The template ships in the repository (20) and the model was trained for tool use with several calls per turn in the template (20). Tool-calling format gets 10, because the card names the qwen3_coder parser but leaves the format to the template. Reasoning control scores 0, since the card shows how to turn thinking on but not where the reasoning comes back. 262,144 tokens is native (10). Structured output scores 0, as nothing documents JSON output for the model. 20+10+20+0+0+10 = 60.

Step 3.7 Flash 85

Chat template 20, chat_template.jinja in the repository (5,723 characters). Tool-calling format 25, the card names the parser to use in two runtimes, step3p5 in vLLM (with auto tool choice) and in SGLang, and both ship Step parsers in a release. Trained tool calling 20, the card presents tool orchestration as a main use, with multi-turn results, and the template renders every call in a turn. Structured output 0, Nothing on the card about JSON or schema-constrained output for the weights. Reasoning control 10, the template has a reasoning_effort setting and keeps reasoning_content, and the card names the step3p5 reasoning parser for vLLM and SGLang, which returns the reasoning apart from the answer. Context 10, 256K tokens per the card, and 262,144 positions in config.json. 20 + 25 + 20 + 0 + 10 + 10 = 85.

Reach Qwen3.5-2B +10

Qwen3.5-2B 80

Memory earns the full 30, since LM Studio's Q4_K_M GGUF with its vision projector is 1.94 GB, about 2.3 GB with the fifth added (Ollama's Q4_K_M build was 1.9 GB on 21 October). Alibaba publishes no quantised 2B, so builds scores 0. Runtimes reach the 25 cap, with llama.cpp b11963 and Ollama through the build it pins re-read today. Apache 2.0 with nothing added gives terms 15 and the ungated download 10. Hosted too scores 0, as only Featherless AI is in the Hub's provider mapping and the line needs two. 30+25+0+15+10+0 = 80.

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.

Risk Qwen3.5-2B +10

Qwen3.5-2B 55

Safetensors only with no remote code gives file safety its 25, and files in the Qwen organisation the publisher's GitHub links to, each with a hash on the Hub, give provenance 15. The Apache 2.0 licence carries none of the deductions, so licence risk keeps 15. Safety evaluation, agent guidance and a security programme score 0, since the card has no safety results or agent cautions and no reporting route was found. The Qwen3.5 blog and Alibaba's security response centre couldn't be read, so those are scored as absent and left open. 25+15+0+0+15+0 = 55.

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 runQwen3.5-2BStep 3.7 FlashEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%258070Qwen3.5-2B +10
Risk20%205545Qwen3.5-2B +10
Agent interface10%106085Step 3.7 Flash +25
Documentation and upkeep10%103739Step 3.7 Flash +2
Negative events≤1500
TotalD 50.5/100C 59.8/100

Facts side by side

FactQwen3.5-2BStep 3.7 Flash
KindOpen-weight modelOpen-weight model
VendorAlibaba (Qwen team)StepFun
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0Apache-2.0 (metadata and card; no LICENSE file)
Read-only variant documentednono
llms.txtnono
Last release2026-03-022026-06-03
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Agent reviews3/5 (4)none

Verdicts

Qwen3.5-2B

A small vision-language model for prototypes, fine-tuning and narrow local steps such as tool calls, tagging or reading an image. It runs in about 2 GB at 4 bits in six runtimes under plain Apache 2.0. Keep thinking off, since the card warns it loops. The card has no safety results, and Qwen has answered none of its discussions.

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

Qwen3.5-2B

  1. Smallest start is ollama run qwen3.5:2b-q4_K_M (1.9 GB); plain qwen3.5:2b pulls the 2.7 GB Q8_0 build
  2. Full precision vllm serve Qwen/Qwen3.5-2B --port 8000 --max-model-len 262144 --enable-auto-tool-choice --tool-call-parser qwen3_coder
  3. Thinking is off by default; if you turn it on with "chat_template_kwargs": {"enable_thinking": true}, stream and cut off runaway output, since the card warns of thinking loops, and add --reasoning-parser qwen3 in vLLM or SGLang to split the reasoning out
  4. There's no generation_config.json, so pass the card's sampling yourself, for example temperature=1.0, top_p=1.0, top_k=20, presence_penalty=2.0 for text without thinking
  5. Use it for narrow steps or as a fine-tuning base, not as the main agent, as the card itself suggests
  6. Validate any JSON it returns, 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, Qwen3.5-2B or Step 3.7 Flash?

Step 3.7 Flash scores 59.8 (C) on agent readiness against Qwen3.5-2B's 50.5 (D), and leads in 2 of 4 scored categories. Qwen3.5-2B leads on reach and risk.

Other comparisons with Qwen3.5-2B 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