- Type
- Open weightsMIT License
- Params
- 358B
- Context
- 205K
about 154K words of context
Our take
Written Aug 3, 2026GLM 4.7 is a large downloadable text model from Z.AI with a permissive MIT licence and a 204,800-token request limit. Its strongest measured skill is coding, though creative writing lags well behind, and the active parameter count remains undisclosed.
Pick this when you need open-weights access to a 358-billion-parameter model with a genuinely permissive licence, or for long-context text work at 204,800 tokens. Use it if you want wide provider choice and can trade cost against speed — the fastest host is over twenty times quicker than the slowest. Skip it if creative writing quality matters, or if you need to verify parameter efficiency claims.
The case for it
- Strongest measured skill is coding, with an Arena Coding Elo 80.3 points above its own creative writing score.
- Permissive MIT licence allows commercial use, modification and redistribution without copyleft requirements.
- 204,800-token request limit is very large for a downloadable model.
- Wide provider choice with a 20.2-fold throughput spread between hosts.
The case against it
- Creative writing is a clear relative weakness, 37.0 points below its own overall text score and 80.3 points below its coding peak.
- Active parameter count not disclosed, so efficiency claims are impossible to verify.
- Top throughput comes at a steep premium: the fastest host charges over five times the cheapest input rate.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)43rd of 143 · 1442.1
CodingWriting and fixing code on its own
Arena Coding47th of 143 · 1485.4
AgenticPlanning, calling tools, staying on task
Nobody we watch has scored GLM 4.7 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 4.7 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 model7 scoresEvery figure we hold, from 7 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.
Comfortable fit
Apple M3 Ultra (80-core GPU) · 512 GB
Room to spare. 149.3 GB spare means a 10% error in the size would not 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 10 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
- $0.40 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 |
|---|---|---|---|---|---|---|
| OpenRouter | $0.40 / $1.75 | 205K | not measured | Unknown | Unknown | Unknown |
| DeepInfrafp4 | $0.40 / $1.75 | 203K | not measured | Unknown | Unknown | Unknown |
| DeepInfrafp4 | $0.40 / $1.75 | 203K | 30 tok/s | No | No | Confirmed |
| AtlasCloudfp8 | $0.52 / $1.85 | 203K | 37 tok/s | No | Yesunknown period | Unknown |
| Novita AIfp8 | $0.54 / $1.98 | 205K | 28 tok/s | No | No | Confirmed |
| Novita AI | $0.60 / $2.20 | 205K | not measured | Unknown | Unknown | Unknown |
| Google Vertex AI | $0.60 / $2.20 | 200K | 111 tok/s | No | No | Confirmed |
| Venice AIfp4 | $0.55 / $2.65 | 198K | 26 tok/s | No | No | Confirmed |
| Cerebrasfp16 | $2.25 / $2.75 | 131K | 225 tok/s | No | No | Confirmed |
| Phala | $0.85 / $3.30 | 131K | 33 tok/s | No | No | Unknown |
DeepInfra
Novita AI
Google Vertex AI
CerebrasAcross the 10 listings we hold: 7 say they do not train on prompts, 0 say they do and 3 do not say. 5 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 | ✓ | ✓ | ✓ |
| DeepInfrafp4 | |||
| DeepInfrafp4 | ✓ | ✓ | ✓ |
| AtlasCloudfp8 | ✓ | ✓ | ✓ |
| Novita AIfp8 | ✓ | ✓ | ✗ |
| Novita AI | |||
| Google Vertex AI | ✓ | ✓ | ✓ |
| Venice AIfp4 | ✓ | ✓ | ✓ |
| Cerebrasfp16 | ✓ | ✓ | ✓ |
| Phala | ✓ | ✓ | ✓ |
Tool calling: 8 of 10 listings say yes, 2 publish no parameter list. JSON output: 8 of 10 listings say yes, 2 publish no parameter list. Strict schema: 7 of 10 listings say yes, 1 says no, 2 publish no parameter list.
Models people weigh against GLM 4.7
When we formed this view
Dates behind this page
Prices last checked 3d 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.
- 2 of 10 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.
- 3 of 10 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-4.7
- Architecture
- Mixture of experts
- Modality record
- text->text
- Catalogue slug
- z-ai-glm-4-7