Back to leaderboard

nemotron-3-nano:4b

OLLAMA GGUF

nemotron_h · 4.0B · Q4_K_M

Excellent

Oct 12, 2026 · AMD Ryzen 5 5500

qwen3.5-4b-mlx

LM-STUDIO MLX

qwen3_5 · 4B · 4bit

Good

Mar 3, 2026 · Apple M4

Global Score
95 vs 71
Hardware Fit
99 vs 88
Quality Score
93 vs 63

Hardware

nemotron-3-nano:4b qwen3.5-4b-mlx
MachineMicrosoft WSLMacBook Air
CPUAMD Ryzen 5 5500Apple M4
Cores1210
RAM8 GB32 GB
GPUIntegrated / UnknownApple M4
OSUbuntu 26.04.1 LTSmacOS 26.3
Archx64arm64
Power Modeunknownbalanced

Performance

nemotron-3-nano:4b qwen3.5-4b-mlx
Tokens/sec107.623.1
First chunk361 ms3279 ms
TTFT1.1 s3.3 s
Load time7.9 sN/A
Memory usage2.6 GB2.9 GB
Memory %34%9%

HW Fit Score Breakdown

nemotron-3-nano:4b

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

qwen3.5-4b-mlx

Speed
45/50
TTFT
13/20
Memory
30/30

Quality

nemotron-3-nano:4b

Reasoning
19/20
Coding
16/20
Instruction
18/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen3.5-4b-mlx

Reasoning
15/20
Coding
16/20
Instruction
6/20
Structured
6/15
Math
11/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Weak Structured Output: Weak Math: Adequate Multilingual: Strong
View nemotron-3-nano:4b details | View qwen3.5-4b-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