muse-glimmer
OLLAMA GGUFSep 5, 2026 · AMD RYZEN AI MAX+ 395
qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-mlx
LM-STUDIO MLXqwen3_moe · 30B · MXFP4
Apr 20, 2026 · Apple M2 Max
Global Score
74 vs 97
Hardware Fit
41 vs 95
Quality Score
88 vs 98
Hardware
muse-glimmer qwen3-30b-a3b-thin…
MachineAZW GTR ProMac Studio
CPUAMD RYZEN AI MAX+ 395Apple M2 Max
Cores3212
RAM125 GB96 GB
GPURadeon 8060SApple M2 Max
OSUbuntu 24.04.4 LTSmacOS 26.1
Archx64arm64
Power Modelow-powerbalanced
Performance
muse-glimmer qwen3-30b-a3b-thin…
Tokens/sec12.179.6
First chunk8749 ms11 ms
TTFT8.7 s1.7 s
Load time0.3 s7.1 s
Memory usage0.0 GB0.0 GB
Memory %0%0%
HW Fit Score Breakdown
muse-glimmer
Speed
10/50
TTFT
1/20
Memory
30/30
qwen3-30b-a3b-thinking-…
Speed
50/50
TTFT
15/20
Memory
30/30
Quality
muse-glimmer
Reasoning
18/20
Coding
18/20
Instruction
13/20
Structured
14/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
qwen3-30b-a3b-thinking-…
Reasoning
19/20
Coding
19/20
Instruction
20/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest