muse-glimmer:30b-mlx-bf16-dflash

1,643 11 hours ago

Meta's latest open model built for always-on local agents. 30B parameters, licensed under Apache 2.0 and runs on a single GPU — tuned for tool use, long tasks, and failure recovery.

vision tools thinking 
ollama run muse-glimmer:30b-mlx-bf16-dflash

Details

11 hours ago

db7968c9dcb3 · 65GB ·

json
{ "bos_token_id": 200000, "eos_token_id": [ 200001, 200008 ], "pad_token_id": 200018, "max_length":
json
{ "image_processor_type": "MuseGlimmerImageProcessor", "processor_class": "MuseGlimmerProcessor", "a
json
{ "processor_class": "MuseGlimmerProcessor", "auto_map": { "AutoProcessor": "processing_muse_glimmer
json
{ "additional_special_tokens": [ "<|begin_of_text|>", "<|end_of_text|>", "<|reserved_special_token_2
json
{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 200000, "content"
json
{ "added_tokens_decoder": { "200000": { "content": "<|begin_of_text|>", "lstrip": false, "normalized
json
{ "video_processor_type": "MuseGlimmerVideoProcessor", "processor_class": "MuseGlimmerProcessor", "a
json
{ "architectures": [ "MuseGlimmerAssistantModel" ], "model_type": "muse_glimmer_assistant", "block_s
params
{ "draft_num_predict": 15, "temperature": 1, "top_k": 64, "top_p": 0.95 }
json
{ "architectures": [ "MuseGlimmerForConditionalGeneration" ], "bos_token_id": 200000, "dtype": "bflo
1495 tensors

Readme

image.png

Note: Muse Glimmer is currently available via initial support via Ollama’s MLX engine on Apple Silicon. Support for NVIDIA, AMD, and other platforms will be available in the coming days.

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.

Benchmarks

Meta evaluated Muse Glimmer across a broad range of benchmarks to assess the diverse capabilities required for effective autonomous agent behavior. Compared with Gemma4-31B and Qwen3.6-27B, Muse Glimmer performs strongly for its size class on several widely used LLM benchmarks.

Category Benchmark Muse Glimmer-30B High Reasoning Gemma4-31B Thinking Mode Qwen3.6-27B Thinking Mode
General Agentic MCP Atlas (Public) 75.5 54.2 62.5
DeepSearch QA 74.6 61.7 71.1
𝛕3-Banking 23.5 15.1 16.7
WildClawBench 47.6 37.6 43.2
GDPVal-AA v2 953 811 1141
Gaia2 43.3 36.4 40.0
SkillsBench (with skills) 44.3 32.4 46.6
OSWorld-Verified 65.9 58.5 75.6
Agentic Coding SWE-Bench Pro 51.2 36.9 50.2
SWE-Bench Verified 76.0 66.6 77.2
TerminalBench 2.1 (with terminus2) 51.7 43.4 60.7
SciCode 43.6 43.4 39.8
Multimodal Charxiv Reasoning 78.8 77.7 78.4
ScreenSpot Pro 75.4 75.9 76.1
OmniDocBench v1.5 75.8 72.5 77.8
MMMU Pro 74 73 75
Safety CI Memories Violation (↓): 26.4
Coverage: 64.8		 Violation (↓): 12.1
Coverage: 53.0		 Violation (↓): 53.4
Coverage: 66.9
Siren AgentDojo Attack Success Rate (↓): 28.4
Utility: 94.2		 Attack Success Rate (↓): 25.6
Utility: 90.8		 Attack Success Rate (↓): 40.3
Utility: 92.7
General Capabilities and Reasoning IFBench 77.0 76.0 70.8
AIME 2026 94.7 89.2 94.1
GPQA Diamond (AA) 83.5 85.7 84.2
HLE Text (AA) 22.0 23.6 23.1
AA-LCR 80.0 68.3 73.3
Beam128K 65.1 58.2 63.0

For more detail about Meta’s evaluations, see Meta’s report.