Back to leaderboard

phi4:latest

OLLAMA GGUF

phi3 · 14.7B · Q4_K_M

Excellent

Sep 15, 2026 · Intel Core™ i5-14400F

nous-hermes2:latest

OLLAMA GGUF

llama · 11B · Q4_0

Good

Mar 1, 2026 · Apple M4

Global Score
85 vs 68
Hardware Fit
100 vs 87
Quality Score
79 vs 60

Hardware

phi4:latest nous-hermes2:latest
MachineGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4MacBook Air
CPUIntel Core™ i5-14400FApple M4
Cores1610
RAM32 GB32 GB
GPUNVIDIA GeForce RTX 5060 TiApple M4
OSMicrosoft Windows 11 Professionnel 10.0.26200macOS 26.3
Archx64arm64
Power Modebalancedbalanced

Performance

phi4:latest nous-hermes2:latest
Tokens/sec38.315.9
First chunk72 msN/A
TTFT72 ms345 ms
Load time6.2 s0.4 s
Memory usage9.1 GB6.6 GB
Memory %29%21%

HW Fit Score Breakdown

phi4:latest

Speed
50/50
TTFT
20/20
Memory
30/30

nous-hermes2:latest

Speed
27/50
TTFT
30/20
Memory
30/30

Quality

phi4:latest

Reasoning
18/20
Coding
19/20
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

nous-hermes2:latest

Reasoning
11/20
Coding
9/20
Instruction
12/20
Structured
15/15
Math
4/15
Multilingual
9/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest