phi4:14b
OLLAMA GGUFphi3 · 14.7B · Q4_K_M
Jun 26, 2026 · Cortex-X925
muse-glimmer
OLLAMA GGUFSep 5, 2026 · AMD RYZEN AI MAX+ 395
Global Score
77 vs 74
Hardware Fit
74 vs 41
Quality Score
78 vs 88
Hardware
phi4:14b muse-glimmer
MachineNVIDIA NVIDIA_DGX_SparkAZW GTR Pro
CPUCortex-X925AMD RYZEN AI MAX+ 395
Cores2032
RAM122 GB125 GB
GPUDevice 2e12Radeon 8060S
OSUbuntu 24.04.4 LTSUbuntu 24.04.4 LTS
Archarm64x64
Power Modeperformancelow-power
Performance
phi4:14b muse-glimmer
Tokens/sec22.912.1
First chunk198 ms8749 ms
TTFT198 ms8.7 s
Load time10.3 s0.3 s
Memory usage14.7 GB0.0 GB
Memory %12%0%
HW Fit Score Breakdown
phi4:14b
Speed
24/50
TTFT
20/20
Memory
30/30
muse-glimmer
Speed
10/50
TTFT
1/20
Memory
30/30
Quality
phi4:14b
Reasoning
18/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
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
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