Muse Glimmer 30B (Meta)
MetaReleased Aug 10, 2026Open weights · Apache 2.0muse-glimmer-30b
- Reasoning
- yes, with effort levels
- Knowledge cutoff
- January 2026
- Context
- 131K tokens
- Max output
- 16k tokens
- Input
- text, image, video
- API features
- tools, structured outputs, JSON mode, seed
Read Oct 23, 06:00 UTC from the hosts' published offers and OpenRouter, spec sheet from Meta · cutoff: huggingface.co
Run it yourself
open weights, Apache 2.0 · fits 6 of the 6 workstations in our guideSelf-host guide ›- Parameters
- 29.78B
- dense
- Memory needed
- 18 GB
- in INT4 · 36 GB in INT8
- Smallest cloud setup
- RTX 3090
- 24 GB · $0.17/h, about $124 a month
- Worth it above
- 83M tokens
- a month, against the cheapest API at $1.50 per M
| Quantization | Memory | Smallest cloud GPU | Quality |
|---|---|---|---|
| INT4 (Q4) | 18 GB | RTX 3090 · $0.17/h | smallest footprint, minor quality loss |
| INT8 (Q8) | 36 GB | A100 · $1.19/h | near-lossless |
| FP16 (full) | 72 GB | A100 · $1.19/h | reference quality |
At home: in INT4 it fits a RTX 5090 (32 GB) + host PC (plus a host PC), about $3,500 once, or $0.1332/h over 3 years, electricity aside; it pays for itself after about 2B tokens against the cheapest API.
Memory ≈ parameters × bytes per parameter × 1.2 · cloud price: on-demand rate, running 24/7 · builds: GGUF, AWQ, MLX, GPTQ, Ollama · break-even calculator
| Provider | Input | Output | Cache ↑ | tok/s | First token | Uptime 24h | Checked |
|---|---|---|---|---|---|---|---|
| DeepInfrabf16 · 128K ctx · 16K out | $0.30 | $1.20 | $0.04 | 34 | 2.35 s | 100% | Oct 23 |
| Together AIfp8 (bf16) · 128K ctx | $0.35 | $1.50 | $0.04 | 91 | 0.26 s | 98.8% | Oct 23 |
2 of 2 providers · prices per million tokens, read Oct 23, 06:00 UTC · speed: OpenRouter, median of the last 30 min, read Oct 23, 06:00 UTC · uptime: OpenRouter, last 24 h · under each host: weights precision, context and max output as served, the maker's value in brackets when the host's differs
| Provider | Weights | Context | Max output | Tools | Structured outputs | Reasoning |
|---|---|---|---|---|---|---|
| DeepInfra | bf16 | 128K | 16K | yes | yes | yes |
| Together AI | fp8 | 128K | not stated by the host | yes | yes | yes |
Weights, context and max output: read at each host's own catalogue or docs where its terms allow, otherwise as the host declares to OpenRouter; hover a cell for its source and date · tools, structured outputs, reasoning: as declared to OpenRouter · not verified by us
Muse Glimmer 30B (Meta) spec sheet, field by field, with sources
Muse Glimmer 30B (Meta) spec sheetmaker-declared
What Meta declares about the model itself — read from its own weights repository and documentation, not from any host. What each endpoint actually serves is in the pricing above: the two can differ, and both are true.
- Context window
- 131,072 tokens
- Parameters
- 29,776,626,688≈ 29.8B
- Active experts
- none declared in the weights
- Weight precision
- BF16
- License
- Apache 2.0 — open weights, permissivecurated · read 2026-10-12Scope: the licence on the published weights, and nothing else. It is not the maker's acceptable-use policy, which is a separate document, and it is not the contract you sign with whichever host you call — hosts set their own terms, which this index does not read.
- Knowledge cutoff
- January 2026maker's docs · read 2026-10-12
- Modalities
- text · image · video
- Max output (official)
- not published by the makermaker's docs · read 2026-10-12
- Release date
- August 10, 2026maker's docs · read 2026-10-12
- Maker lifecycle status
- not published by the makermaker's docs · read 2026-10-12
Also declared in the weights
- Architecture class
- MuseGlimmerForConditionalGeneration
- Layers
- 52
- Vocabulary
- 202,048 tokens
- Weights first published
- August 9, 2026
- Weights last updated
- August 11, 2026
- Papers
- arXiv:2504.13181 · arXiv:2602.06036
meta-models/Muse-Glimmer-30B · config.json @ a4e59da · read 2026-10-12 · 7 of 10 fields published by the maker
| Provider | Chatbot 1,000 in / 500 out | RAG / long context 8,000 in / 500 out | Batch summarize 4,000 in / 1,000 out |
|---|---|---|---|
| DeepInfra | $0.90 | $3.00 | $2.40 |
| Together AI | $1.10 | $3.55 | $2.90 |
What each host bills for 1,000 requests of a representative job
Your own workload
Other Meta models · all its models, hosts and history ›
- Llama 3.3 70B12 providers · from $0.42
- Llama 3.1 8B5 providers · from $0.06
- Llama 4 Maverick5 providers · from $1.00
- Muse Spark Open5 providers · from $5.50
- Llama 3.1 70B Instruct3 providers · from $0.80
- Llama 4 Scout3 providers · from $0.40