bluevoid-pl/Muse-Glimmer-30B-pruned-V2.5-en-pl-GGUF

This GGUF is pruned, so it only contains english + polish characters. It might break/die for no reason. Provided by bluevoid-pl.

Pruning reduces size of model by ~25% allowing you to run model on limited VRAM.

We make no guarantees of any kind that this gguf will work at all.

llama.cpp detects tokenizer changes and might hang for 5min at first start. Warning W load: special_eot_id is not in special_eog_ids - the tokenizer config may be incorrect is expected.

There is partial emoji support in this model.

Vision capabilities are restored compare to previous versions.

Vision requires downloading mmproj-* file. Quantization of vision models usually compound error, so it's recommended to use Q8_0 qwant regardless of your text-text quantization level. Correct file is: mmproj-Muse-Glimmer-30B_pruned-pl-V2.5-Q8_0.gguf.

Note: This model is using English thinking, because of that using Polish language in your prompt is not ideal.

Make sure to use llama.cpp version greater than b10430, model will fail to load on older version.

---

Original Overview is below

Muse Glimmer Model Card

Authors: Meta Superintelligence Lab
Model Release Date: August 2026
License: Apache 2.0

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:

• End-to-end Agentic Task Completion. Muse Glimmer achieves strong success rates on full-task benchmarks including DeepSearch QA, MCP-Atlas, 𝛕3-Bench and SWE-Bench, which measure its ability to work within scaffolds, write and debug code, and resolve multi-turn requests from start to finish.
• Reliable Tool Use. The model handles a wide range of function calls, invoking tools with precise schemas throughout extended workflows.
• Multi-Step Reasoning. Muse Glimmer chains reasoning over long horizons, sustaining coherent plans across complex, extended workflows.
• Failure Recovery. When a tool call fails or returns an unexpected result, the model diagnoses the error and retries rather than halt.
• Multimodal Input and Reasoning. Through a dedicated perception encoder, the model accepts interleaved text and images. This enables agents to interpret screenshots, charts, and documents alongside conversation.
• Scaffold Compatibility. Muse Glimmer works across OpenClaw, Hermes Agent, and other agentic orchestration patterns.
• Controllable Effort. The model supports different reasoning strengths to select the right balance between quality and speed.
• Multilingual. Muse Glimmer is trained on data from more than 100 languages.