Back to leaderboard

deepscaler:1.5b

OLLAMA GGUF

qwen2 · 1.8B · F16

Good

Oct 11, 2026 · AMD Ryzen 5 5500

qwen3.5-9b-mlx

LM-STUDIO MLX

qwen3_5 · 9B · 4bit

Good

Mar 12, 2026 · Apple M4 Pro

Global Score
64 vs 77
Hardware Fit
98 vs 67
Quality Score
49 vs 81

Hardware

deepscaler:1.5b qwen3.5-9b-mlx
MachineMicrosoft WSLMac mini
CPUAMD Ryzen 5 5500Apple M4 Pro
Cores1214
RAM8 GB64 GB
GPUIntegrated / UnknownApple M4 Pro
OSUbuntu 26.04.1 LTSmacOS 15.7.4
Archx64arm64
Power Modeunknownbalanced

Performance

deepscaler:1.5b qwen3.5-9b-mlx
Tokens/sec104.620.3
First chunk849 ms4216 ms
TTFT850 ms4.2 s
Load time10.5 sN/A
Memory usage3.0 GB5.6 GB
Memory %40%9%

HW Fit Score Breakdown

deepscaler:1.5b

Speed
50/50
TTFT
20/20
Memory
28/30

qwen3.5-9b-mlx

Speed
29/50
TTFT
8/20
Memory
30/30

Quality

deepscaler:1.5b

Reasoning
10/20
Coding
6/20
Instruction
10/20
Structured
7/15
Math
11/15
Multilingual
5/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Weak Math: Adequate Multilingual: Weak

qwen3.5-9b-mlx

Reasoning
15/20
Coding
18/20
Instruction
16/20
Structured
14/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View deepscaler:1.5b details | View qwen3.5-9b-mlx 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