Ctrl K
Back to models

Meta

Muse Glimmer

  • Released
  • Open weights
  • Apache 2.0
Compare
Intelligence Index

High setting

17.5#56 of 83measured models
Measured · Artificial Analysis v4.3.2
API price from
$0.30 in / $1.20 out / 1M tokOpenRouter · DeepInfra · BF16
Context window
131.07K tok

Performance profile

ReasoningRank #43 of 107
83.5%
GPQA Diamond
CodingRank #49 of 94
44.9%
SciCode
Cost efficiencyRank #14 of 67
303.6pts / $
Intelligence ÷ eval cost

Capabilities

Context window

Modalities

Measured setting

Integration

Reasoning trade-offs

Source (opens in a new tab)
Intelligence Index v4.3.2
Muse Glimmer
Cost per task (USD) · log scale
Muse GlimmerHigh
Intelligence Index
17.5
Cost / task
$0.0576
Evaluation time
1.8m

Pricing & access

API route
OpenRouter · DeepInfra · BF16API
Tier & contextStandard

USD per 1M tokens

Input
$0.30
Output
$1.20
Cached input
$0.04

Run locally

GGUF
Context
Estimated memory

~20.3 GiB

RAM + VRAM

Estimate assumptions

One text chat at the selected context, with a 16-bit cache and app allowance. Operating system and image processing are extra; optimized caches can use less.

32 GiB RAMwithout GPU offload

Memory budgetOne text chat
Weights
17.9 GiB
Context cache
0.4 GiB16-bit cache
App allowance
2 GiB
Disk space
~31 GBIncludes image file
Available software
Ollama (opens in a new tab)LM Studio (opens in a new tab)Jan (opens in a new tab)KoboldCpp (opens in a new tab)llama.cpp (opens in a new tab)
Get GGUF (opens in a new tab)
Set up in Ollama · Q5_K_M · 8K context

Save the following as Modelfile. The context matches the estimate above.

FROM hf.co/unsloth/Muse-Glimmer-30B-GGUF:Q5_K_M
PARAMETER num_ctx 8192

Then run these commands in your terminal:

ollama create llmcurrent-local -f Modelfile
ollama run llmcurrent-local

Ollama import instructions (opens in a new tab) · For LM Studio or Jan, open the app’s model search, enter unsloth/Muse-Glimmer-30B-GGUF, choose Q5_K_M, and set context to 8,192 tokens in the app’s model settings. Software links above open each app’s setup guide.

Images need extra memoryvLLM setup (opens in a new tab)

Benchmarks

Full leaderboardSource (opens in a new tab)

Humanity’s Last Exam

Frontier reasoning

Muse Glimmer · High#61 of 126

  1. 1Claude Opus 5.5Max61.4%
  2. 2Claude Fable 5.1Max59.1%
  3. 3Gemini 4 ArgonHigh57.1%
  5. 58K2 Horizon MoVA 36B A4BReasoning23.4%
  6. 59Ling-3.0-flash-FinReasoning22.6%
  7. 60Qwen3.6 35B A3BReasoning22.2%
  8. 61Muse GlimmerHigh22.0%
  9. 61Ling-3.0-flash-VLReasoning22.0%
  10. 63Ring-2.6-1TExtra high21.6%
  11. 64o3Reasoning20.1%

Peers use their best measured result on this benchmark.

Alternatives

Each model at its highest-scoring measured setting · Intelligence Index v4.3.2 and its evaluation cost per task.