Muse Glimmer 30B hardware requirements

Open license · Apache-2.0ChatCodingReasoningVision

What is Muse Glimmer 30B?

Muse Glimmer 30B is a dense model that Meta released in August 2026, distilled from Muse Spark for agent work on consumer hardware. It reads text and images, and its model card lists local and coding agents, tool calling and reasoning over screenshots, charts and documents. Thinking cannot be switched off; only its strength can be set, from low to xhigh, with high as the default. The context is 131,072 tokens, and the Apache 2.0 license allows commercial use.

Model card · GGUF card · Release post

About the model

Parameters: 29.78B
Attention: Sliding-window attention
Max context: 131,072 tokens
Released: 2026-08-09
Model card: Muse Glimmer 30B on Hugging Face

GGUF files

Tracked quantizations of Muse Glimmer 30B, smallest first
Quant	File size	Quality	Published by
Q2_K	11.04 GB	Heavy loss	Community GGUF · bartowski
IQ4_XS	15.44 GB	Good balance	Community GGUF · bartowski
Q4_K_Mbaseline	17.31 GB	Good balance	Community GGUF · bartowski
Q8_0	29.61 GB	Near-lossless	Community GGUF · bartowski

File sizes do not include the vision projector (mmproj) that image input needs.

Memory needed by quant and context

Graphics card memory in GB: weights loaded on the GPU + f16 KV cache + compute buffer. Add about 0.6 GB if the GPU also drives your display on Windows. Part of the file stays off the graphics card: llama.cpp keeps the input embedding table in system RAM. A Mac counts the whole file, so it needs a little more.
Quant	4k	8k	16k	32k	64k	128k
Q2_K	11.2	11.3	11.5	11.8	12.6	14.0
IQ4_XS	15.3	15.4	15.6	15.9	16.7	18.2
Q4_K_M	17.1	17.2	17.4	17.8	18.5	20.0
Q8_0	28.8	28.9	29.0	29.4	30.1	31.6

Which GPUs can run Muse Glimmer 30B?

How to read the verdicts

Runs great: Fully on the GPU at 20 tok/s or more
Runs well: Fully on the GPU at 8–20 tok/s; MoE experts in system RAM at 20 tok/s or more; or at least 90% on the GPU at 8 tok/s or more
Runs slowly: 2–8 tok/s; CPU-only; less than 90% on the GPU; or MoE experts in system RAM below 20 tok/s
Won't run: Does not fit, or under 2 tok/s

Dense models split between GPU and CPU slow down sharply — the CPU side sets the pace. MoE models that keep only their experts in system RAM degrade far more gently.

Sort

Filter this list by budget, type and context in the calculator

Scroll sideways to see every column.

56 GPUs, Macs and CPU setups at Q4_K_M with 8k context, sorted by verdict and speed
Hardware	Verdict	Speed	Quant	Memory	Runs as	Context	Notes	Price
GeForce RTX 5090	Runs great	est. 72.0 tok/s63.4–80.7calibrated estimate ±12%	Q4_K_M	17.8 / 32.0 GB	Full GPU	up to 128k	—	$4,200 street (as of 2026-08-09)
Radeon RX 7900 XTX	Runs great	est. 41.9 tok/s36.9–46.9calibrated estimate ±12%	Q4_K_M	17.8 / 24.0 GB	Full GPU	up to 128k	—	$999 launch MSRP
GeForce RTX 3090 Ti	Runs great	est. 40.5 tok/s35.6–45.4calibrated estimate ±12%	Q4_K_M	17.8 / 24.0 GB	Full GPU	up to 128k	—	$1,999 launch MSRP
GeForce RTX 4090	Runs great	est. 40.5 tok/s35.6–45.4calibrated estimate ±12%	Q4_K_M	17.8 / 24.0 GB	Full GPU	up to 128k	—	$2,755 street (as of 2026-08-09)
Apple M5 Ultra · 96 GB	Runs great	est. 40.2 tok/s32.1–48.2calibrated estimate ±20%	Q4_K_M	18.0 / 67.2 GB	Unified memory	up to 128k	—	—
GeForce RTX 3090	Runs great	est. 37.6 tok/s33.1–42.1calibrated estimate ±12%	Q4_K_M	17.8 / 24.0 GB	Full GPU	up to 128k	—	$1,050 street (as of 2026-08-09)
GeForce RTX 5090 Laptop	Runs great	est. 36.0 tok/s31.7–40.3calibrated estimate ±12%	Q4_K_M	17.8 / 24.0 GB	Full GPU	up to 128k	—	—
Radeon RX 7900 XT	Runs great	est. 34.9 tok/s30.7–39.1calibrated estimate ±12%	Q4_K_M	17.8 / 20.0 GB	Full GPU	up to 64k	—	$899 launch MSRP
Apple M3 Ultra · 96 GB	Runs well	est. 26.8 tok/s21.4–32.2calibrated estimate ±20%	Q4_K_M	18.0 / 67.2 GB	Unified memory	up to 128k	Try IQ4_XS: Runs great	—
Apple M5 Max (40-core GPU) · 48 GB	Runs well	est. 26.8 tok/s21.4–32.1calibrated estimate ±20%	Q4_K_M	18.0 / 33.6 GB	Unified memory	up to 128k	Try IQ4_XS: Runs great	—
Apple M2 Ultra · 64 GB	Runs well	est. 26.2 tok/s20.9–31.4calibrated estimate ±20%	Q4_K_M	18.0 / 44.8 GB	Unified memory	up to 128k	Q2_K (heavy quality loss): Runs great	—
Apple M4 Max (40-core GPU) · 48 GB	Runs well	est. 23.8 tok/s19.1–28.6calibrated estimate ±20%	Q4_K_M	18.0 / 33.6 GB	Unified memory	up to 128k	Q2_K (heavy quality loss): Runs great	—
Apple M5 Max (32-core GPU) · 36 GB	Runs well	est. 20.1 tok/s16.1–24.1calibrated estimate ±20%	Q4_K_M	18.0 / 25.2 GB	Unified memory	up to 128k	Q2_K (heavy quality loss): Runs great	—
Apple M4 Max (32-core GPU) · 36 GB	Runs well	est. 17.9 tok/s14.3–21.5calibrated estimate ±20%	Q4_K_M	18.0 / 25.2 GB	Unified memory	up to 128k	—	—
Apple M5 Pro · 48 GB	Runs well	est. 13.4 tok/s10.7–16.1calibrated estimate ±20%	Q4_K_M	18.0 / 33.6 GB	Unified memory	up to 128k	—	—
NVIDIA DGX Spark · 64 GB	Runs well	est. 12.2 tok/s9.8–14.7calibrated estimate ±20%	Q4_K_M	18.0 / 48.2 GB	Unified memory	up to 16k	—	$3,999 launch MSRP (128 GB)
Ryzen AI Max+ 395 (Strix Halo) · 32 GB	Runs well	est. 12.1 tok/s9.6–14.5calibrated estimate ±20%	Q4_K_M	18.0 / 22.4 GB	Unified memory	up to 8k	—	$1,999 launch MSRP (128 GB)
GeForce RTX 5080	Runs slowly	est. 12.5 tok/s10.0–14.9calibrated estimate ±20%	Q4_K_M	16.0 / 16.0 GB + 2.6 GB RAM	Partial offload	up to 128k	Less than 90% on the GPU — a GPU/CPU split is capped at Runs slowly Try IQ4_XS: Runs great	$1,256 street (as of 2026-08-09)
GeForce RTX 5070 Ti	Runs slowly	est. 12.2 tok/s9.8–14.7calibrated estimate ±20%	Q4_K_M	16.0 / 16.0 GB + 2.6 GB RAM	Partial offload	up to 128k	Less than 90% on the GPU — a GPU/CPU split is capped at Runs slowly Try IQ4_XS: Runs great	$949 street (as of 2026-08-09)
GeForce RTX 5080 Laptop	Runs slowly	est. 12.2 tok/s9.8–14.7calibrated estimate ±20%	Q4_K_M	16.0 / 16.0 GB + 2.6 GB RAM	Partial offload	up to 128k	Less than 90% on the GPU — a GPU/CPU split is capped at Runs slowly Try IQ4_XS: Runs great	—
GeForce RTX 4080 Super	Runs slowly	est. 11.5 tok/s9.2–13.8calibrated estimate ±20%	Q4_K_M	16.0 / 16.0 GB + 2.6 GB RAM	Partial offload	up to 128k	Try IQ4_XS: Runs great	$999 launch MSRP
GeForce RTX 4080	Runs slowly	est. 11.4 tok/s9.1–13.7calibrated estimate ±20%	Q4_K_M	16.0 / 16.0 GB + 2.6 GB RAM	Partial offload	up to 128k	Try IQ4_XS: Runs great	$1,199 launch MSRP
Radeon RX 9070	Runs slowly	est. 11.3 tok/s9.0–13.6calibrated estimate ±20%	Q4_K_M	16.0 / 16.0 GB + 2.6 GB RAM	Partial offload	up to 128k	Try IQ4_XS: Runs great	$639 street (as of 2026-08-09)
Radeon RX 9070 XT	Runs slowly	est. 11.3 tok/s9.0–13.6calibrated estimate ±20%	Q4_K_M	16.0 / 16.0 GB + 2.6 GB RAM	Partial offload	up to 128k	Try IQ4_XS: Runs great	$689 street (as of 2026-08-09)
Radeon RX 7800 XT	Runs slowly	est. 11.2 tok/s8.9–13.4calibrated estimate ±20%	Q4_K_M	16.0 / 16.0 GB + 2.6 GB RAM	Partial offload	up to 128k	Try IQ4_XS: Runs great	$499 launch MSRP
GeForce RTX 4070 Ti Super	Runs slowly	est. 11.1 tok/s8.9–13.4calibrated estimate ±20%	Q4_K_M	16.0 / 16.0 GB + 2.6 GB RAM	Partial offload	up to 128k	Try IQ4_XS: Runs great	$799 launch MSRP
GeForce RTX 4090 Laptop	Runs slowly	est. 10.5 tok/s8.4–12.6calibrated estimate ±20%	Q4_K_M	16.0 / 16.0 GB + 2.6 GB RAM	Partial offload	up to 128k	Try IQ4_XS: Runs well Q2_K (heavy quality loss): Runs great	—
GeForce RTX 5060 Ti 16GB	Runs slowly	est. 9.5 tok/s7.6–11.4calibrated estimate ±20%	Q4_K_M	16.0 / 16.0 GB + 2.6 GB RAM	Partial offload	up to 128k	Try IQ4_XS: Runs well	$569 street (as of 2026-08-09)
Radeon RX 9060 XT 16GB	Runs slowly	est. 8.4 tok/s6.7–10.1calibrated estimate ±20%	Q4_K_M	16.0 / 16.0 GB + 2.6 GB RAM	Partial offload	up to 128k	Try IQ4_XS: Runs well	$449 street (as of 2026-08-09)
Apple M4 Pro · 24 GB	Runs slowly	est. 7.8 tok/s5.5–10.2theoretical estimate ±30%	Q4_K_M	17.4 GB RAM	CPU only	up to 128k	Try IQ4_XS: Runs well	—
GeForce RTX 4060 Ti 16GB	Runs slowly	est. 7.6 tok/s6.1–9.1calibrated estimate ±20%	Q4_K_M	16.0 / 16.0 GB + 2.6 GB RAM	Partial offload	up to 128k	Try IQ4_XS: Runs well	$499 launch MSRP
GeForce RTX 3080 12GB	Runs slowly	est. 6.1 tok/s4.8–7.3calibrated estimate ±20%	Q4_K_M	12.0 / 12.0 GB + 6.6 GB RAM	Partial offload	up to 128k	Q2_K (heavy quality loss): Runs great	$799 launch MSRP
GeForce RTX 5070	Runs slowly	est. 5.8 tok/s4.7–7.0calibrated estimate ±20%	Q4_K_M	12.0 / 12.0 GB + 6.6 GB RAM	Partial offload	up to 128k	Q2_K (heavy quality loss): Runs great	$629 street (as of 2026-08-09)
GeForce RTX 5070 Ti Laptop	Runs slowly	est. 5.8 tok/s4.7–7.0calibrated estimate ±20%	Q4_K_M	12.0 / 12.0 GB + 6.6 GB RAM	Partial offload	up to 128k	Q2_K (heavy quality loss): Runs great	—
GeForce RTX 4070	Runs slowly	est. 5.6 tok/s4.5–6.7calibrated estimate ±20%	Q4_K_M	12.0 / 12.0 GB + 6.6 GB RAM	Partial offload	up to 128k	Q2_K (heavy quality loss): Runs great	$599 launch MSRP
GeForce RTX 4070 Super	Runs slowly	est. 5.6 tok/s4.5–6.7calibrated estimate ±20%	Q4_K_M	12.0 / 12.0 GB + 6.6 GB RAM	Partial offload	up to 128k	Q2_K (heavy quality loss): Runs great	$599 launch MSRP
GeForce RTX 4080 Laptop	Runs slowly	est. 5.4 tok/s4.4–6.5calibrated estimate ±20%	Q4_K_M	12.0 / 12.0 GB + 6.6 GB RAM	Partial offload	up to 128k	Q2_K (heavy quality loss): Runs well	—
Intel Arc B580	Runs slowly	est. 5.3 tok/s4.3–6.4calibrated estimate ±20%	Q4_K_M	12.0 / 12.0 GB + 6.6 GB RAM	Partial offload	up to 128k	Q2_K (heavy quality loss): Runs well	$290 street (as of 2026-08-09)
GeForce RTX 3060 12GB	Runs slowly	est. 5.2 tok/s4.2–6.3calibrated estimate ±20%	Q4_K_M	12.0 / 12.0 GB + 6.6 GB RAM	Partial offload	up to 128k	Q2_K (heavy quality loss): Runs well	$250 street (as of 2026-08-09)
GeForce RTX 2080 Ti	Runs slowly	est. 5.2 tok/s4.1–6.2calibrated estimate ±20%	Q4_K_M	11.0 / 11.0 GB + 7.6 GB RAM	Partial offload	up to 128k	—	$999 launch MSRP
GeForce GTX 1080 Ti	Runs slowly	est. 5.0 tok/s3.5–6.5theoretical estimate ±30%	Q4_K_M	11.0 / 11.0 GB + 7.6 GB RAM	Partial offload	up to 128k	—	$699 launch MSRP
Apple M6 · 24 GB	Runs slowly	est. 4.9 tok/s3.4–6.4theoretical estimate ±30%	Q4_K_M	17.4 GB RAM	CPU only	up to 128k	—	—
GeForce RTX 3080 10GB	Runs slowly	est. 4.8 tok/s3.8–5.7calibrated estimate ±20%	Q4_K_M	10.0 / 10.0 GB + 8.6 GB RAM	Partial offload	up to 128k	—	$699 launch MSRP
Apple M5 · 24 GB	Runs slowly	est. 4.4 tok/s3.1–5.7theoretical estimate ±30%	Q4_K_M	17.4 GB RAM	CPU only	up to 128k	—	—
GeForce RTX 3070	Runs slowly	est. 3.9 tok/s3.1–4.6calibrated estimate ±20%	Q4_K_M	8.0 / 8.0 GB + 10.6 GB RAM	Partial offload	up to 64k	—	$499 launch MSRP
GeForce RTX 5060	Runs slowly	est. 3.9 tok/s3.1–4.6calibrated estimate ±20%	Q4_K_M	8.0 / 8.0 GB + 10.6 GB RAM	Partial offload	up to 64k	—	$339 street (as of 2026-08-09)
GeForce RTX 5060 Ti 8GB	Runs slowly	est. 3.9 tok/s3.1–4.6calibrated estimate ±20%	Q4_K_M	8.0 / 8.0 GB + 10.6 GB RAM	Partial offload	up to 64k	—	$429 street (as of 2026-08-09)
GeForce RTX 4060 Ti 8GB	Runs slowly	est. 3.7 tok/s2.9–4.4calibrated estimate ±20%	Q4_K_M	8.0 / 8.0 GB + 10.6 GB RAM	Partial offload	up to 64k	—	$399 launch MSRP
GeForce RTX 4060	Runs slowly	est. 3.7 tok/s2.9–4.4calibrated estimate ±20%	Q4_K_M	8.0 / 8.0 GB + 10.6 GB RAM	Partial offload	up to 64k	—	$299 launch MSRP
GeForce RTX 4060 Laptop	Runs slowly	est. 3.6 tok/s2.9–4.4calibrated estimate ±20%	Q4_K_M	8.0 / 8.0 GB + 10.6 GB RAM	Partial offload	up to 64k	—	—
GeForce RTX 4070 Laptop	Runs slowly	est. 3.6 tok/s2.9–4.4calibrated estimate ±20%	Q4_K_M	8.0 / 8.0 GB + 10.6 GB RAM	Partial offload	up to 64k	—	—
GeForce RTX 3050 8GB	Runs slowly	est. 3.6 tok/s2.8–4.3calibrated estimate ±20%	Q4_K_M	8.0 / 8.0 GB + 10.6 GB RAM	Partial offload	up to 64k	—	$249 launch MSRP
Apple M4 · 24 GB	Runs slowly	est. 3.4 tok/s2.4–4.5theoretical estimate ±30%	Q4_K_M	17.4 GB RAM	CPU only	up to 128k	—	—
DDR5-5600 dual-channel CPU · 96 GB	Won't runTry Q2_K (heavy quality loss): Runs slowly	est. 4.0 tok/s3.2–4.8calibrated estimate ±20%	Q2_K	11.1 GB RAM	CPU only	up to 128k	—	—
DDR5-6000 dual-channel CPU · 96 GB	Won't runTry IQ4_XS: Runs slowly	est. 3.1 tok/s2.5–3.7calibrated estimate ±20%	IQ4_XS	15.5 GB RAM	CPU only	up to 32k	—	—
DDR4-3200 dual-channel CPU · 64 GB	Won't run	est. 1.5 tok/s1.2–1.8calibrated estimate ±20%	Q4_K_M	17.4 GB RAM	CPU only	—	Fits, but too slow to use	—

Models with a thinking mode spend extra tokens thinking, so their speed thresholds are 1.5× stricter (30 / 12 / 3 tok/s). With thinking turned off, a model may do one grade better.

Cheapest GPUs that run it

Runs greatGeForce RTX 3090$1,050 street (as of 2026-08-09), est. 37.6 tok/s (33.1–42.1, calibrated estimate ±12%).

Measured results for Muse Glimmer 30B

No public measurements for this model yet.

Frequently asked questions

How much VRAM does Muse Glimmer 30B need?

At Q4_K_M the file is 17.31 GB; with 8k context a graphics card needs about 17.2 GB (weights 16.54 GB, KV cache 0.1 GB, compute buffer 0.6 GB). The smallest tracked file (Q2_K (heavy quality loss)) needs about 11.3 GB. Part of the file stays off the graphics card: llama.cpp keeps the input embedding table in system RAM. A Mac counts the whole file, so it needs a little more.

What is the cheapest GPU that runs Muse Glimmer 30B well?

Cheapest that runs it great: GeForce RTX 3090 at $1,050 (street price as of 2026-08-09), est. 37.6 tok/s (33.1–42.1, calibrated estimate ±12%).

Can Muse Glimmer 30B run on an 8 GB, 16 GB or 24 GB GPU?

At Q4_K_M with 8k context: GeForce RTX 4060 — Runs slowly, est. 3.7 tok/s (2.9–4.4, calibrated estimate ±20%); GeForce RTX 5060 Ti 16GB — Runs slowly, est. 9.5 tok/s (7.6–11.4, calibrated estimate ±20%); GeForce RTX 3090 — Runs great, est. 37.6 tok/s (33.1–42.1, calibrated estimate ±12%).

Speeds are estimates from memory bandwidth, calibrated against public benchmarks, and each one comes with an error band and a confidence label. Real results vary with drivers, backend, context length and thermals.