Back to leaderboard

neural-chat:7b

llama · 7B · Q4_0

Good

Mar 2, 2026 · Apple M4

qwen3.5:0.8b

qwen35 · 873.44M · Q8_0

Good

Mar 2, 2026 · Apple M4

Global Score
71 vs 70
Hardware Fit
96 vs 99
Quality Score
55 vs 51

Hardware

neural-chat:7b qwen3.5:0.8b
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 qwen3.5:0.8b
Tokens/sec22.548.2
TTFT242 ms195 ms
Load time0.4 s1.0 s
Memory usage4.5 GB2.5 GB
Memory %14%8%

HW Fit Score Breakdown

neural-chat:7b

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

qwen3.5:0.8b

Speed
40/40
TTFT
30/30
Memory
29/30

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

qwen3.5:0.8b

Reasoning
9/20
Coding
6/20
Instruction
11/20
Structured
13/15
Math
5/15
Multilingual
7/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Adequate
View neural-chat:7b details | View qwen3.5:0.8b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running