phi4:14b
OLLAMA GGUFphi3 · 14.7B · Q4_K_M
Jun 26, 2026 · Cortex-X925
glm-4.6v-flash
LM-STUDIO GGUFglm4 · Q4_K_S
Apr 21, 2026 · Apple M2 Max
Global Score
77 vs 65
Hardware Fit
74 vs 88
Quality Score
78 vs 55
Hardware
phi4:14b glm-4.6v-flash
MachineNVIDIA NVIDIA_DGX_SparkMac Studio
CPUCortex-X925Apple M2 Max
Cores2012
RAM122 GB96 GB
GPUDevice 2e12Apple M2 Max
OSUbuntu 24.04.4 LTSmacOS 26.1
Archarm64arm64
Power Modeperformancebalanced
Performance
phi4:14b glm-4.6v-flash
Tokens/sec22.949.9
First chunk198 ms27 ms
TTFT198 ms3.7 s
Load time10.3 s2.7 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
glm-4.6v-flash
Speed
50/50
TTFT
8/20
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
glm-4.6v-flash
Reasoning
0/20
Coding
16/20
Instruction
12/20
Structured
2/15
Math
15/15
Multilingual
10/10
Reasoning: Poor Coding: Strong Instruction Following: Adequate Structured Output: Poor 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