Back to leaderboard

neural-chat:7b

llama · 7B · Q4_0

Good

Mar 2, 2026 · Apple M4

qwen3:0.6b

qwen3 · 751.63M · Q4_K_M

Good

Mar 1, 2026 · Apple M4

Global Score
71 vs 75
Hardware Fit
96 vs 100
Quality Score
55 vs 59

Hardware

neural-chat:7b qwen3:0.6b
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 qwen3:0.6b
Tokens/sec22.5143.9
TTFT242 ms1.4 s
Load time0.4 s0.9 s
Memory usage4.5 GB4.1 GB
Memory %14%13%

HW Fit Score Breakdown

neural-chat:7b

Speed
36/40
TTFT
30/30
Memory
30/30

qwen3:0.6b

Speed
40/40
TTFT
30/30
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

qwen3:0.6b

Reasoning
14/20
Coding
0/20
Instruction
11/20
Structured
13/15
Math
13/15
Multilingual
8/10
Reasoning: Adequate Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running