Back to leaderboard

neural-chat:7b

llama · 7B · Q4_0

Good

Mar 2, 2026 · Apple M4

qwen3.5:2b

qwen35 · 2.3B · Q8_0

Good

Mar 2, 2026 · Apple M4

Global Score
67 vs 73
Hardware Fit
96 vs 100
Quality Score
55 vs 62

Hardware

neural-chat:7b qwen3.5:2b
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 qwen3.5:2b
Tokens/sec22.530.4
TTFT242 ms215 ms
Load time0.4 s1.8 s
Memory usage4.5 GB4.5 GB
Memory %14%14%

HW Fit Score Breakdown

neural-chat:7b

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

qwen3.5:2b

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

qwen3.5:2b

Reasoning
12/20
Coding
10/20
Instruction
13/20
Structured
14/15
Math
4/15
Multilingual
9/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View neural-chat:7b details | View qwen3.5:2b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running