Back to leaderboard

qwen3.5-2b-mlx

LM-STUDIO MLX

qwen3_5 · 2B · 4bit

Good

Mar 6, 2026 · Apple M4 Pro

hermes3:8b

OLLAMA GGUF

llama · 8.0B · Q4_0

Good

Mar 6, 2026 · Apple M4

Global Score
65 vs 74
Hardware Fit
88 vs 94
Quality Score
55 vs 65

Hardware

qwen3.5-2b-mlx hermes3:8b
MachineMac miniMacBook Air
CPUApple M4 ProApple M4
Cores1410
RAM64 GB32 GB
GPUApple M4 ProApple M4
OSmacOS 15.7.4macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5-2b-mlx hermes3:8b
Tokens/sec48.922.3
First chunk4208 ms296 ms
TTFT4.2 s296 ms
Load timeN/A0.8 s
Memory usage1.6 GB10.2 GB
Memory %3%32%

HW Fit Score Breakdown

qwen3.5-2b-mlx

Speed
50/50
TTFT
8/20
Memory
30/30

hermes3:8b

Speed
44/50
TTFT
20/20
Memory
30/30

Quality

qwen3.5-2b-mlx

Reasoning
10/20
Coding
7/20
Instruction
13/20
Structured
14/15
Math
3/15
Multilingual
8/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong

hermes3:8b

Reasoning
11/20
Coding
10/20
Instruction
14/20
Structured
15/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3.5-2b-mlx details | View hermes3:8b 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