Local AI Advisor

Can Desktop PC · Radeon RX 7900 XT · 32 GB RAM run Muse Glimmer (30B)?

20 GB VRAM + 32 GB RAM · 800 GB/s memory bandwidth · Muse Glimmer (30B) has 29.6B parameters.

Short answer

Yes, excellent for chat; borderline for 64K-token documents.

Best quantization for chat: Q4_K_M (16 GB of weights) on Lemonade. Generation: 25–40 tok/s, leaving about 1.9 GB free for your other apps.

How it rates for each workload

Same model and machine, different jobs. Agents and long documents send far bigger prompts than chat, so they need much more speed and memory.

WorkloadVerdictQuantGenerationFirst replyContext
Chatwith Open WebUIExcellentQ4_K_M25–40 tok/s≈1 s8KDetails
Coding questionswith ContinueExcellentQ4_K_M25–40 tok/s≈7 s16KDetails
Coding in a repositorywith AiderAcceptableQ4_K_M25–40 tok/s≈25 s32KDetails
Agentic codingwith OpenCodeAcceptableQ4_K_M25–40 tok/s≈30 s32KDetails
Long documents (64K)with Open WebUIBorderlineQ4_K_M25–40 tok/s≈2 min64KDetails

Speeds are bandwidth-based estimates; no direct benchmark exists for this pair. “First reply” is the time to read the workload’s opening prompt. How we calculate

Different tool, context size or workload?

These pages use typical settings. The full check models your exact setup.