Back to leaderboard

neural-chat:7b

OLLAMA GGUF

llama · 7B · Q4_0

Good

Mar 2, 2026 · Apple M4

glm4:9b

OLLAMA GGUF

chatglm · 9.4B · Q4_0

Good

Mar 6, 2026 · Apple M4

Global Score
67 vs 76
Hardware Fit
96 vs 88
Quality Score
55 vs 71

Hardware

neural-chat:7b glm4:9b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

neural-chat:7b glm4:9b
Tokens/sec22.519.0
First chunkN/A290 ms
TTFT242 ms290 ms
Load time0.4 s0.8 s
Memory usage4.5 GB8.1 GB
Memory %14%25%

HW Fit Score Breakdown

neural-chat:7b

Speed
36/50
TTFT
30/20
Memory
30/30

glm4:9b

Speed
38/50
TTFT
20/20
Memory
30/30

Quality

neural-chat:7b

Reasoning
7/20
Coding
9/20
Instruction
12/20
Structured
12/15
Math
7/15
Multilingual
8/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

glm4:9b

Reasoning
14/20
Coding
15/20
Instruction
14/20
Structured
13/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong 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