Hacker ApprovedDepartments

GLM-4.5 Air

Shares rank 31 of 39 open-weight language models by recommenders

Free open-weight model that people run locally and rate highly for coding and general use. Some report weaker performance on certain tasks.

Free open-weight model that people run locally and rate highly for coding and general use. Some report weaker performance on certain tasks.

11 people gave an opinion

recommend it
9
criticize it
2
approval share
82%
Each figure is one person. RecommendsCriticizes

Recommended in 5 of 13 months

  1. November 2025: recommended
  2. December 2025: recommended
  3. January 2026: recommended
  4. February 2026: not recommended
  5. March 2026: recommended
  6. April 2026: not recommended
  7. May 2026: not recommended
  8. June 2026: recommended
  9. July 2026: not recommended
  10. August 2026: not recommended
  11. September 2026: not recommended
  12. October 2026: not recommended
  13. November 2026: not recommended (month in progress)

Why it doesn’t carry the badge

  • 9 people recommend itNeeds 10 or more, not met.
  • 4.5 recommenders for every criticNeeds 2 to 1 or better, met.
  • Recommended in 5 of 13 monthsNeeds 4 or more, met.

The same three rules apply to every product, and the badge can’t be bought. How the badge works

What people say about it

The reasons people give, with the number of comments that give each one. Open a reason to read what they said.

Why people recommend it

Each mark is one comment

  • Runs locally and fits on hardware

    “I've gotten great results out of glm-4.5-air which is 4.5 distilled down to 110B params which can fit nicely at 8 bits”

    Comment from 23 Dec 2025 in “GLM-4.7: Advancing the Coding Capability”

    “you can also run something like GPT OSS 120B or GLM 4.5 Air locally.”

    Comment from 7 Jan 2026 in “A 30B Qwen Model Walks into a Raspberry Pi and Runs in Real Time”

    “both easily fit and run incredibly fast”

    Comment from 23 Dec 2025 in “GLM-4.7: Advancing the Coding Capability”
  • Good results across tasks, including coding

    “I limit myself to models with <144B params, then it's quite an enjoyable experience. GLM 4.5 Air has been great in particular”

    Comment from 1 Dec 2025 in “DeepSeek-v3.2: Pushing the frontier of open large language models [pdf]”

    “I've gotten great results out of glm-4.5-air which is 4.5 distilled down to 110B params which can fit nicely at 8 bits”

    Comment from 23 Dec 2025 in “GLM-4.7: Advancing the Coding Capability”

    “is fantastic all around (including coding)”

    Comment from 10 Nov 2025 on Hacker News

What people warn about

Each mark is one comment

  • Performance drops on some tasks

    “it delegates certain tasks to glm-4.5 air and that drops performance a ton”

    Comment from 23 Dec 2025 in “GLM-4.7: Advancing the Coding Capability”

    “the community darling GLM-4.5-Air got 50%”

    Comment from 2 Jan 2026 in “Dell's version of the DGX Spark fixes pain points”

Other open-weight language models people recommend

The four most recommended other open-weight language models, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.

GLM-4.5 Air compared with 4 alternatives
ProductRecommendCriticizeApprovalMonthsOwnedBadge
Qwen 3.8 27B1,17342673%132 mo32 ownersApproved
Z.ai GLM1,04338473%132 mo52 ownersApproved
Kimi93135972%131 mo26 ownersApproved
Gemma 471324974%131 mo14 ownersApproved
GLM-4.5 AirThis page9282%5——
See all 39 open-weight language models, ranked

What people said

10 of the 11 comments that mention it, newest first. Each links to the original comment.

“perhaps GLM 5 Air model is also around this size”

MixedComment from 18 Jun 2026 in “Ask HN: Whats the best and small open source model?”

“worse than glm air 4.5 IMO”

RecommendsComment from 17 Mar 2026 in “Mistral Small 4”

“OpenRouter has free models (eg Z.ai: GLM 4.5 Air), I recommend those.”

RecommendsComment from 11 Mar 2026 in “Show HN: Klaus – OpenClaw on a VM, batteries included”

“you can also run something like GPT OSS 120B or GLM 4.5 Air locally.”

MixedComment from 7 Jan 2026 in “A 30B Qwen Model Walks into a Raspberry Pi and Runs in Real Time”

“the community darling GLM-4.5-Air got 50%”

CriticizesComment from 2 Jan 2026 in “Dell's version of the DGX Spark fixes pain points”

“both easily fit and run incredibly fast”

RecommendsComment from 23 Dec 2025 in “GLM-4.7: Advancing the Coding Capability”

“it delegates certain tasks to glm-4.5 air and that drops performance a ton”

CriticizesComment from 23 Dec 2025 in “GLM-4.7: Advancing the Coding Capability”

“I've gotten great results out of glm-4.5-air which is 4.5 distilled down to 110B params which can fit nicely at 8 bits”

RecommendsComment from 23 Dec 2025 in “GLM-4.7: Advancing the Coding Capability”

“I limit myself to models with <144B params, then it's quite an enjoyable experience. GLM 4.5 Air has been great in particular”

RecommendsComment from 1 Dec 2025 in “DeepSeek-v3.2: Pushing the frontier of open large language models [pdf]”

“is fantastic all around (including coding)”

RecommendsComment from 10 Nov 2025 on Hacker News

Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.