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

GLM-4.5-Air vs Qwen3-Coder-30B-A3B-Instruct

GLM-4.5-Air scores 59.1 (C) on agent readiness against Qwen3-Coder-30B-A3B-Instruct's 55.7 (C), and leads in 4 of 5 scored categories. Qwen3-Coder-30B-A3B-Instruct 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-Coder-30B-A3B-InstructAlibaba (Qwen team) · Open-weight model C55.7/100#78 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 33
Risk, 65 against 55
Agent interface, 85 against 75
Documentation and upkeep, 38 against 31

Watch for

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

Qwen3-Coder-30B-A3B-Instruct C

Best for Coding agents and local coding tools that want a fast, capable open model on one 24 GB GPU or a 32 GB Mac, with a plain licence.

Ahead on

Reach, 90 against 65

Watch for

No safety results, prompt-injection guidance or security contact, though it's meant to run commands

Score by category

Category	Weight this run	GLM-4.5-Air	Qwen3-Coder-30B-A3B-Instruct	Edge
Capability	35%35	50	33	GLM-4.5-Air +17
Reach	25%25	65	90	Qwen3-Coder-30B-A3B-Instruct +25
Risk	20%20	65	55	GLM-4.5-Air +10
Agent interface	10%10	85	75	GLM-4.5-Air +10
Documentation and upkeep	10%10	38	31	GLM-4.5-Air +7
Negative events	≤15	0	0
Total		C 59.1/100	C 55.7/100

Facts side by side

Fact	GLM-4.5-Air	Qwen3-Coder-30B-A3B-Instruct
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	2025-12-03
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-Coder-30B-A3B-Instruct

A fast coding cousin, with 3.3B of 30.5B parameters active per token, for agentic coding tools, repository reading and fill-in-the-middle without a thinking step. It needs about 21 to 23 GB at 4 bits, and several providers host it. The main risk is that it runs commands for agents with no safety results or guidance, and Alibaba doesn't answer users.

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-Coder-30B-A3B-Instruct

Quickest start is ollama run qwen3-coder:30b, 19 GB
On our reference machine use BF16 with vllm serve Qwen/Qwen3-Coder-30B-A3B-Instruct --max-model-len 262144 --enable-auto-tool-choice --tool-call-parser qwen3_coder, 61 GB of weights fits the GPU share
Use the qwen3_coder parser in vLLM or SGLang, not hermes, since calls come back as function and parameter blocks rather than JSON
Pass tool-call arguments in the history as objects, the template iterates them as a mapping
Sampling per the card is temperature 0.7, top_p 0.8, top_k 20 and repetition_penalty 1.05, with up to 65,536 output tokens
For code completion use the fill-in-the-middle tokens <|fim_prefix|>, <|fim_suffix|> and <|fim_middle|> from Qwen's README
Sandbox the commands and files it touches, since nothing from Alibaba covers prompt injection

Questions

Which is better for AI agents, GLM-4.5-Air or Qwen3-Coder-30B-A3B-Instruct?

GLM-4.5-Air scores 59.1 (C) on agent readiness against Qwen3-Coder-30B-A3B-Instruct's 55.7 (C), and leads in 4 of 5 scored categories. Qwen3-Coder-30B-A3B-Instruct leads on reach.

Other comparisons with GLM-4.5-Air or Qwen3-Coder-30B-A3B-Instruct

Machine-readable

This page as Markdown /compare/glm-4-5-air-vs-qwen3-coder-30b-a3b-instruct.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-coder-30b-a3b-instruct.json
From a terminal anchor compare glm-4-5-air qwen3-coder-30b-a3b-instruct (the CLI)
Over MCP compare_tools {"a": "glm-4-5-air", "b": "qwen3-coder-30b-a3b-instruct"} at /mcp, no key

Which one, for what

Score by category

Facts side by side

Verdicts

GLM-4.5-Air

Qwen3-Coder-30B-A3B-Instruct

Before you call either

GLM-4.5-Air

Qwen3-Coder-30B-A3B-Instruct

Questions

Which is better for AI agents, GLM-4.5-Air or Qwen3-Coder-30B-A3B-Instruct?

Other comparisons with GLM-4.5-Air or Qwen3-Coder-30B-A3B-Instruct

Machine-readable

Do agents find, use and choose your tools?