Edge0 AILanguage modelWeights available
Edge0-145B
43out of 100first value
usage data only, range 30 to 57
Summary
Edge0-145B is a language model for local coding and agent tasks. Edge0 reports that 10.12 billion of its 145 billion parameters are active per token.
Edge0 publishes the weights in Q3_K and NVFP4. Both formats store weights at reduced precision to save memory. Commercial model services require a separate license.
On this page
Popularity compared
How often the model is searched for, used and mentioned, compared with every model of its category.
Popularity index
The 100 most popular models of this category, 0 to 100, higher is more popular
20 of 101 models
As of November 2026 · Source: gradually.ai popularity index
Over time
First value from November 15, 2026. The timeline appears from the second week.
What is gaining popularity right now, across models, vendors, harnesses and AI subscriptions, is collected in All AI trends.
Similar models
More models of the same kind as Edge0-145B, chosen by model line, developer, size, price and release date.
- Edge0-120BEdge0 AI · same developer
- Qwen 3.8 Flash NextAlibaba · similar size
- Mixtral 8x22BMistral AI · similar size
- Mistral Medium 3.5Mistral AI · similar size
- WizardLM-2 8x22BMicrosoft · similar size
- Ling 3.0 FlashinclusionAI · similar size
- Step 3.7 FlashStepFun · similar size
- DBRXDatabricks · similar size
All specifications
Architecture
Input and output
- Context limit in the launch template
- The launch template caps context at 131,072 tokens. The model configuration lists 262,144 tokens.
- Source: Context limit in the launch template
Watermarking and provenance
AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.
- AI watermarking
- Unknown
- no source
- Watermarking technique
- Not known
- no source
Licence and access
- Weights license
- Edge0 Community Model License 1.0. Qwen components remain subject to the Qwen Community License 1.0.
- Source: Weights license
- Shutdown
- None announced
- no source
Further details
- Tested hardware
- Edge0 ran the Q3_K weights locally on an RTX 5090 D with a test budget of 16 GiB of video memory and 20 GiB of system RAM. These figures describe the test setup.
- Source: Tested hardware
- Commercial deployment
- Selling the model, running a commercial model service, and offering standalone commercial coding or office assistants require a separate written license from Edge0.
- Source: Commercial deployment
Frequently asked questions about Edge0-145B
How large is the context window of Edge0-145B?
262,144 tokens. That is how much text Edge0-145B reads at once, about 390 A4 pages.
Page count as a rule of thumb from Artificial Analysis
Can I run Edge0-145B locally?
Yes, the weights are open. Edge0 ran the Q3_K weights locally on an RTX 5090 D with a test budget of 16 GiB of video memory and 20 GiB of system RAM. These figures describe the test setup.
Stated by Edge0 AI
- Open weights
- yes
- License
- Edge0 Community Model License 1.0. Qwen components remain subject to the Qwen Community License 1.0.
- Parameters
- 145B
- active per token
- 10.1B
Sources and data date
Show all 12 sources
| Type | Evidence and data date |
|---|---|
| Input | Documented modalities. Retrieved November 13, 2026. |
| Output | Documented modalities. Retrieved November 13, 2026. |
| Additional source | Edge0 release announcement (retrieved November 13, 2026) |
| Additional source | Edge0 release log (retrieved November 13, 2026) |
| Additional source | Edge0-145B model configuration (retrieved November 13, 2026) |
| Additional source | Edge0-145B NVFP4 model card (retrieved November 13, 2026) |
| Additional source | Edge0 Community Model License 1.0 (retrieved November 13, 2026) |
| Additional source | OpenRouter: Popularity index (derived), CC BY 4.0 |
| Additional source | Vercel AI Gateway: Popularity index (derived), CC BY 4.0 |
| Additional source | Ollama: cumulative downloads for the popularity index |
| Additional source | Replicate: cumulative runs for the popularity index |
| Additional source | Google Trending Now: limited feed selection for Germany and the US |
| Additional source | Creative Commons Attribution 4.0 |