Model reference · open weights
Muse-Glimmer-assistant is an open-weight language model from meta-models. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.
Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.
What it is
| Released by | meta-models |
|---|---|
| Type | Language models |
| Task | Vision + text |
| Parameters (lead) | 2.6B |
| Context | 128k tokens |
| Runs with | transformers |
| Released | 2026-08-09 |
| Popularity | 27k downloads / month |
| Licence | Open weights |
About
Authors: Meta Superintelligence Lab Model Release Date: August 2026 License: Apache 2.0
[!NOTE] This model card is for the lightweight "drafter" model for Muse Glimmer 30B, based on DFlash. The DFlash block-diffusion model predicts entire blocks of 16 tokens in a single forward pass. The main model then verifies these proposals in parallel, accepting correct tokens and correcting wrong ones. This technique lets Muse Glimmer generate text significantly faster than standard token-by-token generation while producing identical output quality.
Muse Glimmer is a 30-billion-parameter causal language model with a dedicated perception encoder, distilled from Muse Spark and purpose-built for autonomous agentic tasks on consumer hardware. The model integrates multi-step reasoning, reliable tool use, multimodal understanding, and failure recovery into a single model that runs locally without requiring cloud infrastructure or network access.
Building effective agents requires key capabilities working together to achieve the user’s goals. Muse Glimmer is trained and evaluated on these capabilities:
| Model Architecture | Dense Causal Transformer with Perception Encoder |
|---|---|
| Total Parameters | ~29.6B |
| Language Model | |
| Architecture | Dense Causal Transformer |
| Number of Parameters | 29.6B (including vision encoder) |
| Hidden dimension | 6656 |
| Layers | 52 |
| Attention pattern | [Local, Local, Local, Global] repeating |
| Sliding window size | 2048 |
| Gated attention | Yes |
| Attention heads (Q / KV) | 32 / 2 (GQA ratio 16:1) |
| Head dimension | 128 |
| FFN type | SwiGLU |
| FFN intermediate dimension | 19,968 |
| Position encoding | RoPE (θ = 500,000), local layers only |
| Perception encoder | ~1.8B param ViT-G/14, 50 layers, width 1536, patch size 14 |
| Vocabulary size | 202,048 |
| Tokenizer | 200,000 BPE tokens + 2,048 special tokens |
| Max visual tokens per image | 4,096 |
| Context length | 131,072+ |
| Supported modalities | Input: text + image, Output: text |
| Training Data | Multimodal content sourced from publicly available data, data provided by third parties and information from Meta's products and services, curated and enriched by external vendor networks and Meta personnel. |
| Knowledge cutoff | January 4, 2026 |
Muse Glimmer was optimized for local deployment, and designed to run at practical speeds on consumer hardware without sacrificing quality.
Fitting the Model on Your Device. We use quantization techniques to compress the model's weights to approximately 4-bit precision, shrinking the language model to under 20 GB. This leaves enough headroom for the model's KV cache, the perception encoder for image understanding, and the speculative decoding drafter to run simultaneously within a 24 GB or 32 GB envelope. Critically, we validated that this compression introduces minimum to no degradation on agentic tasks.
| Full Precision | K-Quant-Dynamic | K-Quant-17GB | |
|---|---|---|---|
| % Degradation* | - | 0.2% | 1.0% |
| Target Hardware | 64GB VRAM | 32GB VRAM | 24GB VRAM |
* Degradation measured using an average on accuracy metrics across 15 common benchmarks
Faster Generation Through Speculative Decoding Muse Glimmer ships with a lightweight "drafter" model based on DFlash, a small companion network that proposes entire blocks of tokens at once. The DFlash block-diffusion model predicts entire blocks of 16 tokens in a single forward pass. The main model then verifies these proposals in parallel, accepting correct tokens and correcting wrong ones. This technique lets Muse Glimmer generate text significantly faster than standard token-by-token generation while producing identical output quality. We provide quantized drafter versions to incur a smaller memory overhead in the release.
| Component | Setting |
|---|---|
| Draft layers | 5 |
| Block size | 16 |
| Attention | Sliding-window, 2048, all layers |
| Attention heads | 32 query / 8 KV (GQA) |
| Sequence length | 131,072 |
| Hidden-feature layers | 5, uniform over target: {1, 13, 25, 37, 49} of 52 |
We measure the speed of our K-Quant-17GB model alongside the quantized DFlash drafter on MacBook M4-Max, M5-Max and on an Nvidia RTX-5090. The model is fast enough for fluid conversation and real-time agent interaction, all running entirely on your device.
| GPU | Baseline No-s
From the published model card. Full card on the HuggingFace links in the sidebar.
Using it via the API
Once AxForge deploys muse-glimmer-assistant for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (muse-glimmer-assistant below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"muse-glimmer-assistant","messages":[{"role":"user","content":"Hello"}]}'
Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.