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

GLM-4.5-Air vs Qwen3.5-0.8B

GLM-4.5-Air scores 59.1 (C) on agent readiness against Qwen3.5-0.8B's 46.7 (D), and leads in 4 of 5 scored categories. Qwen3.5-0.8B leads on reach. 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

GLM-4.5-AirZ.ai (Zhipu AI) · Open-weight model C59.1/100#62 of 100 open-weight models Qwen3.5-0.8BAlibaba (Qwen team) · Open-weight model D46.7/100#97 of 100 open-weight models

Which one, for what

GLM-4.5-Air C

Best for Agents with two to four datacentre GPUs, or a provider account, who want a permissively licensed English and Chinese tool-calling model with wide runtime support.

Ahead on

Capability, 50 against 17
Risk, 65 against 55
Agent interface, 85 against 60

Watch for

Z.ai's smallest build is FP8 at about 135 GB in use, with no 4-bit build of its own

Qwen3.5-0.8B D

Best for Builders who want a near-free local helper or fine-tuning base for narrow tasks on a phone-class device, laptop or CPU

Ahead on

Reach, 80 against 65

Watch for

No quantised build from Alibaba and no inference provider found

Score by category

Category	Weight this run	GLM-4.5-Air	Qwen3.5-0.8B	Edge
Capability	35%35	50	17	GLM-4.5-Air +33
Reach	25%25	65	80	Qwen3.5-0.8B +15
Risk	20%20	65	55	GLM-4.5-Air +10
Agent interface	10%10	85	60	GLM-4.5-Air +25
Documentation and upkeep	10%10	38	37	GLM-4.5-Air +1
Negative events	≤15	0	0
Total		C 59.1/100	D 46.7/100

Facts side by side

Fact	GLM-4.5-Air	Qwen3.5-0.8B
Kind	Open-weight model	Open-weight model
Vendor	Z.ai (Zhipu AI)	Alibaba (Qwen team)
Hosted endpoint	no (local only)	no (local only)
Transports
Auth	None	None
Pricing	Free	Free
x402	no	no
Licence	MIT	Apache-2.0
Read-only variant documented	no	no
llms.txt	no	no
Last release	2025-08-11	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	2.8/5 (4)	2.8/5 (4)

Verdicts

GLM-4.5-Air

An English and Chinese cousin for agent, coding and tool-calling work, with switchable thinking and wide runtime support. It needs about 135 GB for Z.ai's FP8 build, two to four H100s by Z.ai's figures, and Z.ai and Novita host it. The main risk is age, with files from August 2025 and no answers from Z.ai since.

Qwen3.5-0.8B

A tiny vision-language cousin for prototypes, fine-tuning and light local steps such as routing, tagging or reading an image, running in under 2 GB in every major runtime under plain Apache 2.0. Keep thinking off, since the card warns it loops. The main risk is neglect, with no hosted option, safety results or answers from Alibaba since March.

Before you call either

GLM-4.5-Air

Z.ai's FP8 recipe is python3 -m sglang.launch_server --model-path zai-org/GLM-4.5-Air-FP8 --tp-size 4 --tool-call-parser glm45 --reasoning-parser glm45, and 2 H100s are enough below the full 128K context
Use the glm45 tool and reasoning parsers for this model, the glm47 parser in Z.ai's current README is for GLM-4.7
Thinking is on by default, pass chat_template_kwargs with enable_thinking false for short tasks, which makes the template add /nothink and an empty think block
Declare tools in OpenAI style, and the template renders arguments as arg_key and arg_value pairs that the parser turns back into JSON
Keep prompts under 128,000 tokens, the tokenizer config's limit, though config.json allows 131,072
Validate JSON output yourself or use the runtime's guided decoding, since structured output isn't documented for the weights

Qwen3.5-0.8B

Smallest start is ollama run qwen3.5:0.8b, or qwen3.5:0.8b-q8_0 at 1.0 GB
Full precision vllm serve Qwen/Qwen3.5-0.8B --port 8000 --max-model-len 262144 --enable-auto-tool-choice --tool-call-parser qwen3_coder
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
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
Use it for narrow steps or as a fine-tuning base, not as the main agent, as the card itself suggests
Validate any JSON it returns, since structured output isn't documented

Questions

Which is better for AI agents, GLM-4.5-Air or Qwen3.5-0.8B?

GLM-4.5-Air scores 59.1 (C) on agent readiness against Qwen3.5-0.8B's 46.7 (D), and leads in 4 of 5 scored categories. Qwen3.5-0.8B leads on reach.

Other comparisons with GLM-4.5-Air or Qwen3.5-0.8B

Machine-readable

This page as Markdown /compare/glm-4-5-air-vs-qwen3-5-0-8b.md · slim .min.md · JSON .json (or send Accept: text/markdown)
Each listing in full /api/v1/tools/glm-4-5-air.json · /api/v1/tools/qwen3-5-0-8b.json
From a terminal anchor compare glm-4-5-air qwen3-5-0-8b (the CLI)
Over MCP compare_tools {"a": "glm-4-5-air", "b": "qwen3-5-0-8b"} 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