Back to leaderboard

qwen3.5:4b-mlx

OLLAMA GGUF

nvfp4

Marginal

Aug 24, 2026 · Apple M2

Nemotron-3-Nano-Omni-30B-A3B-Reasoning-Q4_K_M:latest

OLLAMA GGUF

nemotron_h_moe · 31.6B · Q4_K_M

Excellent

Aug 19, 2026 · AMD Ryzen 7 9700X 8-Core Processor

Global Score
53 vs 81
Hardware Fit
82 vs 78
Quality Score
41 vs 82

Hardware

qwen3.5:4b-mlx Nemotron-3-Nano-Om…
MachineMac miniMicro-Star International Co., Ltd. MS-7E51
CPUApple M2AMD Ryzen 7 9700X 8-Core Processor
Cores816
RAM8 GB31 GB
GPUApple M2NVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OSmacOS 26.5.2Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3.5:4b-mlx Nemotron-3-Nano-Om…
Tokens/sec24.756.8
First chunk302 ms421 ms
TTFT7.4 s421 ms
Load time3.2 s0.1 s
Memory usage3.8 GB26.0 GB
Memory %47%84%

HW Fit Score Breakdown

qwen3.5:4b-mlx

Speed
50/50
TTFT
6/20
Memory
26/30

Nemotron-3-Nano-Omni-30…

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

Quality

qwen3.5:4b-mlx

Reasoning
13/20
Coding
2/20
Instruction
4/20
Structured
4/15
Math
10/15
Multilingual
8/10
Reasoning: Adequate Coding: Poor Instruction Following: Poor Structured Output: Weak Math: Adequate Multilingual: Strong

Nemotron-3-Nano-Omni-30…

Reasoning
14/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
10/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3.5:4b-mlx details | View Nemotron-3-Nano-Om… 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