Home
LLMs
Muse Glimmer 30B

Muse Glimmer 30B

Meta's first open release since Llama 4: a 29.6B dense model (including a 1.8B perception encoder) distilled from Muse Spark, tuned for agentic tasks on a single consumer GPU, under Apache 2.0.

Params: 29.6B
Context: 131K tokens
Cutoff: Jan 2026
Released: Aug 2026
License: Apache 2.0

Visit Meta Compare vs other LLMs →

Hosted API price

Cheapest via EmpirioLabs AI · per 1M tokens

USD

Input: $0.20 /1M
Output: $0.80 /1M
Hosted by: 3 providers

Hosted API pricing

How we price

Order

Providers are listed cheapest input rate first, then by output rate, a tie going to the creator's own listing. A provider that lists the model without a published rate sits at the end.

Prices

Base-tier, on-demand rates in USD per 1M tokens, converted at ECB reference rates where a provider publishes in another currency. Cached-input and batch rates show only where a provider publishes them. "Cheapest" marks the one provider with the lowest input and output pair; a tie wears no badge.

Cost

Input rate times the input tokens plus output rate times the output tokens, at the monthly volume set above the table. Cached-input, batch, long-context and reasoning-token billing are not modelled.

Transparency and funding

Affiliates: Affiliate links are marked. We may earn a commission if you click them, but commissions never affect the order.

Every provider serving Muse Glimmer 30B, cheapest input first. Set your monthly volume to see what each would bill.

Input M Output M

Every provider serving Muse Glimmer 30B, with its price per 1M input and output tokens and what the volume above would cost
Provider	Input /1M	Output /1M	Cached input /1M	Cost at 10M in + 2M out	Link
EmpirioLabs AI Cheapest	$0.20	$0.80	$0.05	$3.60	Visit website
Together AI	$0.35	$1.50	$0.04	$6.50	Visit website
Meta Creator	Open weights, no hosted price				Visit website

Heads up: Base-tier, on-demand rates per 1M tokens; cached, batch and long-context tiers excluded. A provider may serve a shorter context or a quantized build than the creator's release. Verify before provisioning. More on how we price.

Estimated cost to self-host

Muse Glimmer 30B needs about 22 GB of GPU memory at 4-bit with 32K context. The cheapest rental that fits is 2× RTX 4060 Ti at about $173 a month.

That costs the same as roughly 576M tokens a month on EmpirioLabs AI's API. Self-hosting is more expensive below that volume.

Single node ≤ 8

What it costs to self-host Muse Glimmer 30B at each precision: the memory it needs, the cheapest rental that holds it, that rental's month and the API volume it pays off at
Precision	Memory	Cheapest fit (32K context)(Full 131K context)	Cost /mo	Break-even vs API
4-bit INT4 / FP4	22 GB35 GB	2× RTX 4060 Ti	$173$346	576M tokens /mo1B tokens /mo
8-bit FP8 / INT8	40 GB48 GB	4× RTX 3060	$202$346	672M tokens /mo1B tokens /mo
16-bit FP16 / BF16	69 GB94 GB	8× RTX 3060	$403$691	1B tokens /mo2B tokens /mo

Estimates based on median on-demand rates for Nvidia GPUs. Memory is weights plus KV cache for one request, using FP8 KV cache where supported and FP16/BF16 otherwise. KV cache assumed at 250 KB per token, a conservative default. Break-even assumes a 5:1 input-to-output ratio. No guarantee of runtime support, usable performance, or that a matching quantized build exists. How we estimate costs.

Similarly priced models

The models nearest Muse Glimmer 30B by blended rate, each at its own cheapest provider.

Models priced nearest Muse Glimmer 30B per 1M tokens, each at its cheapest provider
Model	Blended /1M	Input /1M	Output /1M	Context	Cutoff	vs Muse Glimmer 30B
Qwen3-Coder-Next Alibaba Cloud	$0.23	$0.08	$0.98	262K		−23%
Llama 4 Scout Meta	$0.24	$0.16	$0.64	10M	Aug 2024	−20%
Qwen3.5-122B-A10B Alibaba Cloud	$0.2533	$0.12	$0.92	262K		−16%
Llama 4 Maverick Meta	$0.2833	$0.20	$0.70	1M	Aug 2024	−6%
Qwen3-VL-30B-A3B Instruct Alibaba Cloud	$0.2833	$0.20	$0.70	262K		−6%
Muse Glimmer 30B This model Meta	$0.30	$0.20	$0.80	131K	Jan 2026
Qwen2.5-7B Instruct Alibaba Cloud	$0.30	$0.30	$0.30	33K		0%
Qwen3-235B-A22B FP8 Alibaba Cloud	$0.30	$0.20	$0.80	33K		0%
Qwen3.5-397B-A17B Alibaba Cloud	$0.3133	$0.17	$1.03	262K		+4%
MiniMax-M3 MiniMax	$0.3167	$0.20	$0.90	1M		+6%
Qwen3-Next-80B-A3B Instruct Alibaba Cloud	$0.325	$0.15	$1.20	262K		+8%

USD per 1M tokens at each model's cheapest listed provider. Blended is the cost of 10M input plus 2M output tokens, spread over the 12M.

Salad

Access 60,000+ daily active GPUs across 191 countries, from $0.02/hour

Run RTX 50-series and 40-series cards without datacenter pricing

Pick a priority level to balance cost against interruptions

Per-second billing, with no charge for cold starts or image pulls

View Pricing

Capabilities

What Muse Glimmer 30B accepts and can do, as published by Meta.

Text Accepts and generates natural-language text.
Image Accepts images as input alongside text.
Reasoning Thinks before it answers, always on or as a switchable mode.
Function calling Connect to external tools, APIs, and systems.

Common questions

What is Muse Glimmer 30B good for?

Local agents and coding agents. Apache 2.0 weights, sized to fit a single consumer GPU.

When is Muse Glimmer 30B not a good fit?

Video input, structured output, web search or MCP, none of which it has. In Meta's lineup those come with the closed-weight Muse Spark API models.

What is the cheapest way to run Muse Glimmer 30B?

Hosted, unless you push serious volume. EmpirioLabs AI charges $0.20 in / $0.80 out per 1M tokens. The cheapest rental that fits is 2x RTX 4060 Ti at $173 a month, which costs the same as about 576M tokens a month on that API.

Can I self-host Muse Glimmer 30B?

Yes. The weights are Apache 2.0 licensed. At 4-bit it needs about 22 GB of GPU memory, which starts at roughly $173 a month on the cheapest rental that fits.