GLM 4.6V
Z.AI · released Dec 7, 2025 · zai-org/GLM-4.6V
- Type
- Open weightsMIT License
- Params
- 108B
- Context
- 131K
about 98K words of context
Our take
Written Aug 3, 2026GLM 4.6V is a 108-billion-parameter multimodal model from Z.AI that accepts text, images and video, with a permissive MIT licence and particular strength on coding leaderboards. It handles up to 131,072 tokens in a single request and is available from four hosts.
Pick this for coding-heavy workloads where its Arena Coding score is the headline, or for open-weights multimodal inference that needs MIT licence flexibility. Use it for long-context work up to 131,072 tokens, or when you want provider choice. Skip it if creative writing quality is the priority, or if you need a measured active parameter count to judge per-token compute costs.
The case for it
- Strongest measured skill is coding: its Arena Coding Elo is 41.4 points above its own overall text score, and 74.3 points above its creative writing score.
- Fully permissive MIT licence allows commercial use, modification and redistribution without copyleft requirements.
- Fastest throughput on the vendor's own infrastructure, at more than double the speed of the next measured host.
The case against it
- Creative writing lags other Arena categories, sitting 33 points below its overall text score and 74.3 points below its coding score.
- No measured active parameter count, so the total 107.7 billion may overstate per-token compute if the architecture is sparse or mixture-of-experts.
- Throughput is unverified on half of listed providers, with no measurement for OpenRouter and one Novita entry.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)88th of 143 · 1377.2
CodingWriting and fixing code on its own
Arena Coding93rd of 143 · 1418.6
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Nobody we watch has scored GLM 4.6V for this. We would take the rating from Arena Agent (IPS).
WritingWe do not rate this
Two boards come close and neither tests writing: Arena Creative Writing asks people which of two replies they prefer, and LiveBench Language tests whether a model understood a passage. So we show where GLM 4.6V placed and give it no mark out of five.
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, which is why they get no rating.
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?
- Fits in memory
- weights load entirely on the card
- Spills to system RAM
- some weights offload; much slower
- Too large
- will not load even with offload
- est
- size is calculated; the verdict could change by 10%
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.
All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.
Check against your own machine → · All 71 devices, with every size →
Or rent it from someone else
Cheapest of 4 live listings. Picked at the widest standard context we hold, within one quantisation slice, so the numbers beside it are a price one host actually charges.
- 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 |
|---|---|---|---|---|---|---|
| OpenRouter | $0.30 / $0.90 | 131K | not measured | Unknown | Unknown | Unknown |
| Novita AI | $0.30 / $0.90 | 131K | not measured | Unknown | Unknown | Unknown |
| Novita AIbf16 | $0.30 / $0.90 | 131K | 19 tok/s | No | No | Confirmed |
| Z.AIfp8 | $0.30 / $0.90 | 131K | 39 tok/s | No | No | Confirmed |
Novita AIAcross the 4 listings we hold: 2 say they do not train on prompts, 0 say they do and 2 do not say. 2 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✓ | ✓ | ✗ |
| Novita AI | |||
| Novita AIbf16 | ✓ | ✓ | ✗ |
| Z.AIfp8 | ✓ | ✗ | ✗ |
Tool calling: 3 of 4 listings say yes, 1 publishes no parameter list. JSON output: 2 of 4 listings say yes, 1 says no, 1 publishes no parameter list. Strict schema: 0 of 4 listings say yes, 3 say no, 1 publishes no parameter list.
Models people weigh against GLM 4.6V
When we formed this view
Dates behind this page
Prices last checked 4d ago
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.
- 1 of 4 listings publish no parameter list, so what their API accepts is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 2 of 4 listings do not say whether they train on prompts.
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
- Modality record
- text+image+video->text
- Catalogue slug
- z-ai-glm-4-6v