- Type
- Open weightsMIT License
- Params
- 357B
- Context
- 205K
active per word not recorded by us · about 154K words of context
Our take
Written Sep 30, 2026GLM 4.6 is a downloadable text model with a licence that allows commercial use, changes and redistribution, and it resolves real GitHub issues end-to-end better than most of the field on that board. Its measured quality sits mid-table on the Arena boards, and running it yourself is a serious hardware undertaking.
Pick it when a permissive licence and a model you can download matter more than a placing near the top of the Arena boards, or when you want to reach it through a host rather than run it yourself. It is a reasonable fit for coding work: 13th of 42 on SWE-bench Verified as of 19 Feb 2026, which measures the share of real GitHub issues resolved end-to-end. Skip it if you need a model that places near the top of the Arena boards, or if your hardware cannot hold a model this size.
The case for it
- The MIT License allows commercial use, changes and redistribution, so a commercial product can be built on it.
- 13th of 42 on SWE-bench Verified as of 19 Feb 2026, which measures the share of real GitHub issues resolved end-to-end rather than set-piece exercises.
- Seven hosted offers are listed, so you can try it through a host before committing to the download.
The case against it
- 76th of 168 on Arena Text (overall) and 86th of 168 on Arena Coding as of 25 Sep 2026, both human-preference boards rather than correctness tests.
- 356.8 billion parameters in total, with no figure supplied for how many work on any one token, so the memory needed is not something we can estimate.
- The Arena placings record which answer people preferred, not whether it was right.
How good is it?
EverydayGeneral questions and everyday reasoning
Arena Text (overall)76th of 168 · 1424
CodingWriting and fixing code on its own
Arena Coding86th of 168 · 1458
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent. It is on SWE-bench Verified, in 13th of 42 with 68.2.
WritingDrafting and rewriting prose
Arena Creative Writing69th of 168 · 1400
Arena Creative Writing is the only board that has scored it for this.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done.
Every published score for this model8 scoresEvery figure we hold, from 8 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Can you run it yourself?
GeForce RTX 4090 · 24 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Apple M1 Pro (16-core GPU) · 32 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Comfortable fit
Apple M3 Ultra (80-core GPU) · 512 GB
Room to spare. 150.3 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first.
Check against your own machine → · Where to rent it hosted →
Or rent it from someone else
Prices checked 4 hours ago — each listing carries its own date.
- per 1M tokens
- $0.43 in / $1.75 out
- Context served
- 205K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| Venice AIfp4Through OpenRouter | $0.43 / $1.75checked 4 hours ago | 198K16K max reply | 56 tok/s | No | No | Confirmed |
| OpenRouterOpenRouter's own listing | $0.43 / $1.75checked 4 hours ago | 205K | not measured | Unknown | Unknown | Unknown |
| DeepInfrafp4Direct and through OpenRouter | $0.50 / $2.00checked 4 hours ago | 203K131K max reply through OpenRouter | 20 tok/sthrough OpenRouter | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterConfirmed |
| Novita AIbf16Direct and through OpenRouter | $0.55 / $2.20checked 4 hours ago | 205K131K max reply through OpenRouter | 25 tok/sthrough OpenRouter | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterConfirmed |
| Z.AIfp4Through OpenRouter | $0.60 / $2.20checked 4 hours ago | 203K131K max reply | 25 tok/s | No | No | Confirmed |
DeepInfra
Novita AIAcross the 5 listings we hold: 4 say they do not train on prompts (2 of them only through OpenRouter), 0 say they do and 1 does not say. 4 appear in the zero-retention registry we check (2 of them only through OpenRouter); the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| Venice AIfp4Through OpenRouter | ✓ | ✓ | ✓ |
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| DeepInfrafp4Direct and through OpenRouter | ✓ | ✗ | ✗ |
| Novita AIbf16Direct and through OpenRouter | ✓ | ✓ | ✗ |
| Z.AIfp4Through OpenRouter | ✓ | ✗ | ✗ |
Tool calling: 5 of 5 listings say yes. JSON output: 3 of 5 listings say yes, 2 say no. Strict schema: 2 of 5 listings say yes, 3 say no.
Models people weigh against GLM 4.6
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- We do not hold the active parameter count for it, so how much of it runs on any one token is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 5 listings does not say whether it trains on prompts, and 2 answer only through OpenRouter, not for their own listing.
- We hold no batch or off-peak rate for any of its listings.
- We hold a decode speed for it, but no prompt-processing (prefill) figure, so how long the input side of a job takes is unknown to us.
Licence and identifiers
What the licence allowsMIT License, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
MIT License
Fully permissive: do anything with attribution. No patent grant, unlike Apache-2.0.
Identifiers
- Hugging Face
- zai-org/GLM-4.6
- Architecture
- Mixture of experts
- Takes in, gives back
- Text in, text out
- Catalogue slug
- z-ai-glm-4-6