whatmodel.sh / Mage-VL-Cowork
Mage-VL-Cowork
↗ share
+ contribute
Mage-VL-Cowork is an open-weights language model from Microsoft, released October 2026. Its published size is 4.74B parameters and a 33k-token context window. Licence: apache-2.0.
Catalogue identity notes
Microsoft Mage Team 4B hybrid computer-use agent (GUI computer_use + bash) trained from an intermediate Mage-VL checkpoint (Mage-ViT + Qwen3-4B-Instruct-2507) with a five-stage curriculum ending in online RL; image+text -> text, custom llava_onevision2 architecture needing trust_remote_code. Specialised for desktop/terminal agent use with its own system prompt and tool schema, not a general chat model. Weights released 2026-10-30 (commit 6fbe7f9 'Release Mage-VL-Cowork model weights, card, and OSWorld evaluation reference'). Only the final RL checkpoint's OSWorld-Verified figure is assigned; Stage-1 grounding scores (OSWorld-G, ScreenSpot-v2) and the WebVoyager-Static score (Mage-VL-Cowork-SFT checkpoint) belong to other checkpoints. GGUF builds are ggml-org automatic conversions. No API.
Model information sources
Release date ↗ · Weights licence ↗ · Parameter count ↗
Card states '4B (9.48 GB in bfloat16 across 2 safetensors shards)'; 4.74 is the HF safetensors metadata count (4,741,793,792 BF16 parameters at sha 6fbe7f9), which includes the Mage-ViT vision encoder. Dense (Qwen3-4B-Instruct-2507 language backbone).
$ how it compares
Scored LLMs released closest to Mage-VL-Cowork, out of 1206 with a score, then more from Microsoft.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 3 | 84±1 | api $4.00/M | |||
| 6 | 83±1 | api $2.00/M | |||
| 10 | 81±1 | Muse Code only | |||
| 19 | 78±1 | api price unknown | |||
| 20 | 78±1 | api $8.00/M | |||
| more from Microsoft | |||||
| 345 | 58±1 | local | |||
| 368 | 57±1 | api $0.22/M +local | |||
| 523 | 53±1 | api $0.087/M +local | |||
$ what it's good at
agent tasksnot ranked on this task yet · 1 test
| test | result | vs the others in its run | counts |
|---|---|---|---|
| OSWorld-Verified lab | 66.0% ✎ | █▃·▂▅▂▅▂▅▃▆▆ beats 14/28 | — |
$ where to run it
Memory is what a version takes in GPU memory (or a Mac's unified memory) with an 8k-token conversation. With less, it runs partly from system RAM, more slowly. Enter your machine to see what runs at full speed.
Other ways to run it
version
- Run it as published · needs 4.7 GB memory, 3.07 GB download · from huggingface.co/ggml-org
llama serve -hf ggml-org/Mage-VL-Cowork-GGUF
Model repository and documentation: huggingface.co/microsoft ↗
$ published results · 1 result, not enough overlap for a score
| test | result | source and conditions |
|---|---|---|
| OSWorld-Verified | 66.0% | microsoft/Mage-VL-Cowork model card · maker-reported Microsoft Mage Team own evaluation in the pinned Mage-VL-Cowork card, section '1. Main Desktop Results: OSWorld-Verified', row 'Mage-VL-Cowork-4B (Ours)', column 'Overall' = 66.0; protocol text gives the unrounded 66.04% as the two-run average (65.33% run 1, 66.75% run 2). 361 OSWorld-Verified tasks excluding Google Drive, 50-step budget, MAGEHybridAgent harness (history_n=3, images_to_keep=3, 1920x1080), temperature 0.7, top_p 0.8, max_new_tokens 4096. Success rate, final Online-RL checkpoint. Other rows in that table are other models (some with 100-step budgets) and are not used. |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json