Back to leaderboard

qwen3.5:latest

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Not Rec.

Mar 8, 2026 · Apple M4

cogito:3b

OLLAMA GGUF

llama · 3.6B · Q4_K_M

Good

Mar 6, 2026 · Apple M4

Global Score
34 vs 67
Hardware Fit
58 vs 100
Quality Score
23 vs 53

Hardware

qwen3.5:latest cogito:3b
MachineMac miniMacBook Air
CPUApple M4Apple M4
Cores1010
RAM16 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5:latest cogito:3b
Tokens/sec13.345.6
First chunk438 ms177 ms
TTFT19.8 s177 ms
Load time0.2 s0.8 s
Memory usage8.0 GB7.0 GB
Memory %50%22%

HW Fit Score Breakdown

qwen3.5:latest

Speed
32/50
TTFT
1/20
Memory
25/30

cogito:3b

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

Quality

qwen3.5:latest

Reasoning
6/20
Coding
1/20
Instruction
3/20
Structured
0/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Weak Multilingual: Strong

cogito:3b

Reasoning
6/20
Coding
8/20
Instruction
13/20
Structured
15/15
Math
2/15
Multilingual
9/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
View qwen3.5:latest details | View cogito:3b details

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