GLM 4.6V
Z.ai · released Dec 7, 2025 · zai-org/GLM-4.6V
- Type
- Open weightsMIT License
- Params
- 108B
- Context
- 131K
active per word not recorded by us · about 98K words of context
Our take
Written Sep 30, 2026GLM 4.6V is a model you can download and run yourself, with a licence that allows commercial use, changes and redistribution. It takes text, images and video in and returns text, and its measured quality sits in the lower half of the field on every board we hold.
Pick it when a screenshot, diagram or clip goes in with the question and the answer comes back as text, or when you need permissive terms for a commercial project. Its request capacity is large enough that a long report or a stack of documents need not be split up first, though reliable recall across all of it is unverified in our data. Skip it if you need a model near the top of a preference board for chat, writing or coding, or if you need a figure for how many parameters work per token.
The case for it
- Images and video go into the same request as the text, so a screenshot or a clip does not have to be described in words first.
- The licence allows commercial use, changes and redistribution (MIT).
- A long report or a stack of documents fits beside the question, though room to hold it is not a guarantee of accurate recall.
The case against it
- Middling on every board we hold: 110th of 168 on Arena Text (overall) as of 25 Sep 2026, 100th of 168 on Arena Creative Writing as of 25 Sep 2026, and 118th of 168 on Arena Coding as of 25 Sep 2026 — human preference votes, not correctness scores.
- No figure for how many parameters work per token, so the memory it needs in use cannot be judged from the facts here.
How good is it?
EverydayGeneral questions and everyday reasoning
Arena Text (overall)110th of 168 · 1379
CodingWriting and fixing code on its own
Arena Coding118th of 168 · 1416
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent.
WritingDrafting and rewriting prose
Arena Creative Writing100th of 168 · 1350
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 model5 scoresEvery figure we hold, from 5 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.
Apple M2 Max (38-core GPU) · 96 GB
Borderline fit on an estimated size. It leaves 0.5 GB spare on a size we calculated rather than measured, and a 10% error either way would 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
- $0.30 in / $0.90 out
- Context served
- 131K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.30 / $0.90checked 4 hours ago | 131K | not measured | Unknown | Unknown | Unknown |
| Novita AIbf16Direct and through OpenRouter | $0.30 / $0.90checked 4 hours ago | 131K33K max reply through OpenRouter | 38 tok/sthrough OpenRouter | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterConfirmed |
| Z.AIfp8Through OpenRouter | $0.30 / $0.90checked 4 hours ago | 131K33K max reply | 36 tok/s | No | No | Confirmed |
Novita AIAcross the 3 listings we hold: 2 say they do not train on prompts (1 of them only through OpenRouter), 0 say they do and 1 does not say. 2 appear in the zero-retention registry we check (1 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 |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✗ |
| Novita AIbf16Direct and through OpenRouter | ✓ | ✓ | ✗ |
| Z.AIfp8Through OpenRouter | ✓ | ✗ | ✗ |
Tool calling: 3 of 3 listings say yes. JSON output: 2 of 3 listings say yes, 1 says no. Strict schema: 0 of 3 listings say yes, 3 say no.
Models people weigh against GLM 4.6V
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 3 listings does not say whether it trains on prompts, and 1 answers only through OpenRouter, not for its 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-4.6V
- Architecture
- Mixture of experts
- Takes in, gives back
- Text, images and video in, text out
- Catalogue slug
- z-ai-glm-4-6v