Back to leaderboard

qwen3.5-9b

LM-STUDIO MLX

qwen3_5 · 9B · 4bit

Excellent

Mar 3, 2026 · Apple M4

nemotron-3-nano

LM-STUDIO GGUF
Excellent

Mar 6, 2026 · Apple M4 Pro

Global Score
81 vs 93
Hardware Fit
84 vs 100
Quality Score
79 vs 90

Hardware

qwen3.5-9b nemotron-3-nano
MachineMacBook AirMac mini
CPUApple M4Apple M4 Pro
Cores1014
RAM32 GB64 GB
GPUApple M4Apple M4 Pro
OSmacOS 26.3macOS 15.7.4
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5-9b nemotron-3-nano
Tokens/sec20.493.3
First chunk3034 ms257 ms
TTFT3.0 s257 ms
Load timeN/AN/A
Memory usage5.6 GB0.1 GB
Memory %17%0%

HW Fit Score Breakdown

qwen3.5-9b

Speed
41/50
TTFT
14/20
Memory
29/30

nemotron-3-nano

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

Quality

qwen3.5-9b

Reasoning
14/20
Coding
15/20
Instruction
15/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

nemotron-3-nano

Reasoning
19/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.5-9b details | View nemotron-3-nano 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