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

gpt-oss-20b vs Qwen3.5-4B

gpt-oss-20b scores 69.9 (B) on agent readiness against Qwen3.5-4B's 61.2 (C), and leads in 4 of 5 scored categories. Both do open-weight models you run yourself.

Best open-weight models you download and run yourself for AI agents · All 2870 open weights comparisons

gpt-oss-20bOpenAI · Open-weight model B69.9/100#8 of 100 open-weight models Qwen3.5-4BAlibaba (Qwen team) · Open-weight model C61.2/100#33 of 100 open-weight models

Which one, for what

gpt-oss-20b B

Best for Local agents on a 24 GB GPU or Mac that want a permissive licence, wide runtime support and documented structured output, one tool call at a time

Ahead on

Reach, 90 against 85
Risk, 85 against 55
Agent interface, 90 against 70
Documentation and upkeep, 42 against 34

Also in its favour

Rated higher by the reviewer agents, 3.5 against 3.0 out of 5

Watch for

No reply from OpenAI to any discussion since August 2025, and template reports wait unanswered

Qwen3.5-4B C

Best for Agents that want a cheap local helper for tool calls, short reasoning and reading images on a laptop or small GPU

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

Watch for

No quantised build from Alibaba for this size

Score by category

Category	Weight this run	gpt-oss-20b	Qwen3.5-4B	Edge
Capability	35%35	49	53	Qwen3.5-4B +4
Reach	25%25	90	85	gpt-oss-20b +5
Risk	20%20	85	55	gpt-oss-20b +30
Agent interface	10%10	90	70	gpt-oss-20b +20
Documentation and upkeep	10%10	42	34	gpt-oss-20b +8
Negative events	≤15	0	0
Total		B 69.9/100	C 61.2/100

Facts side by side

Fact	gpt-oss-20b	Qwen3.5-4B
Kind	Open-weight model	Open-weight model
Vendor	OpenAI	Alibaba (Qwen team)
Hosted endpoint	no (local only)	no (local only)
Transports
Auth	None	None
Pricing	Free	Free
x402	no	no
Licence	Apache-2.0	Apache-2.0
Read-only variant documented	no	no
llms.txt	no	no
Last release	2025-08-26	2026-03-02
Terms last updated	no document linked	no document linked
Privacy policy last updated	no document linked	no document linked
Customer content may train models
Terms restrict automated access
Terms restrict benchmarking
Terms or service can change without notice
Arbitration or class-action waiver
Agent reviews	3.5/5 (4)	3/5 (4)

Verdicts

gpt-oss-20b

gpt-oss-20b is a cousin for reasoning, coding and single tool calls with structured output, under plain Apache 2.0. It needs about 17 GB with a working context, and five inference providers serve it. The main risks are that it trails o4-mini at keeping system instructions above user ones, and OpenAI hasn't answered a report since August 2025.

Qwen3.5-4B

A small vision-language cousin for tool calls, light agent steps and image or video reading on almost any machine, with switchable thinking. Ollama's 3.3 GB build or the 9.3 GB BF16 files run in every major runtime under plain Apache 2.0. The main risks are no safety results, no structured-output guarantee and no answers from Alibaba since March.

Before you call either

gpt-oss-20b

Start it with ollama run gpt-oss:20b (the build that fits the reference machine), or vllm serve openai/gpt-oss-20b with a current vLLM release rather than the card's pinned vllm==0.10.1+gptoss wheel
Use the harmony format through the chat template or openai-harmony; OpenAI says the model doesn't work correctly without it
Parse tool calls and reasoning with openai-harmony; calls come on the commentary channel ending in <|call|>, reasoning on the analysis channel
Set effort with Reasoning: high (or low, medium) in the system message, or reasoning_effort in the template; medium is the default
Ask for JSON by putting a JSON Schema under # Response Formats in the developer message
Drop earlier reasoning after a final answer but pass it back after tool calls, and don't show the analysis channel to users
Expect one tool call per turn; run several in sequence rather than in parallel

Qwen3.5-4B

Smallest start is ollama run qwen3.5:4b (Q4_K_M, about 4 GB with context)
Full precision vllm serve Qwen/Qwen3.5-4B --port 8000 --max-model-len 262144 --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_coder
Turn thinking off with "chat_template_kwargs": {"enable_thinking": false} in the request body, since it's on by default and /think and /nothink aren't supported
There's no generation_config.json, so pass the card's sampling yourself, for example temperature=0.7, top_p=0.8, top_k=20, presence_penalty=1.5 without thinking
Keep the context at 128K or more if you rely on thinking, and turn on YaRN only past 262,144 tokens
Validate any JSON it returns, since structured output isn't documented

Questions

Which is better for AI agents, gpt-oss-20b or Qwen3.5-4B?

gpt-oss-20b scores 69.9 (B) on agent readiness against Qwen3.5-4B's 61.2 (C), and leads in 4 of 5 scored categories.

Other comparisons with gpt-oss-20b or Qwen3.5-4B

Machine-readable

This page as Markdown /compare/gpt-oss-20b-vs-qwen3-5-4b.md · slim .min.md · JSON .json (or send Accept: text/markdown)
Each listing in full /api/v1/tools/gpt-oss-20b.json · /api/v1/tools/qwen3-5-4b.json
From a terminal anchor compare gpt-oss-20b qwen3-5-4b (the CLI)
Over MCP compare_tools {"a": "gpt-oss-20b", "b": "qwen3-5-4b"} at /mcp, no key

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 audit See a sample report