Back to leaderboard

nemotron-3-super:latest

OLLAMA GGUF

nemotron_h_moe · 123.6B · Q4_K_M

Good

Oct 3, 2026 · Cortex-X925

qwen2.5-7b-instruct

LM-STUDIO MLX

qwen2 · 7B · 4bit

Excellent

Mar 3, 2026 · Apple M4

Global Score
74 vs 84
Hardware Fit
50 vs 97
Quality Score
84 vs 78

Hardware

nemotron-3-super:l… qwen2.5-7b-instruct
MachineNVIDIA NVIDIA_DGX_SparkMacBook Air
CPUCortex-X925Apple M4
Cores2010
RAM122 GB32 GB
GPUDevice 2e12Apple M4
OSUbuntu 24.04.5 LTSmacOS 26.3
Archarm64arm64
Power Modeperformancebalanced

Performance

nemotron-3-super:l… qwen2.5-7b-instruct
Tokens/sec21.824.4
First chunk420 ms464 ms
TTFT2.2 s464 ms
Load time12.4 sN/A
Memory usage79.5 GB4.0 GB
Memory %65%13%

HW Fit Score Breakdown

nemotron-3-super:latest

Speed
23/50
TTFT
10/20
Memory
17/30

qwen2.5-7b-instruct

Speed
47/50
TTFT
20/20
Memory
30/30

Quality

nemotron-3-super:latest

Reasoning
17/20
Coding
18/20
Instruction
11/20
Structured
14/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

qwen2.5-7b-instruct

Reasoning
14/20
Coding
17/20
Instruction
15/20
Structured
15/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View nemotron-3-super:l… details | View qwen2.5-7b-instruct 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