Back to leaderboard

nemotron-3-super:latest

OLLAMA GGUF

nemotron_h_moe · 123.6B · Q4_K_M

Good

Oct 3, 2026 · Cortex-X925

mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Oct 20, 2026 · Apple M1 Pro

Global Score
74 vs 73
Hardware Fit
50 vs 64
Quality Score
84 vs 77

Hardware

nemotron-3-super:l… mistralai/devstral…
MachineNVIDIA NVIDIA_DGX_SparkMacBook Pro
CPUCortex-X925Apple M1 Pro
Cores2010
RAM122 GB32 GB
GPUDevice 2e12Apple M1 Pro
OSUbuntu 24.04.5 LTSmacOS 15.6.1
Archarm64arm64
Power Modeperformancebalanced

Performance

nemotron-3-super:l… mistralai/devstral…
Tokens/sec21.811.9
First chunk420 ms7 ms
TTFT2.2 s1.1 s
Load time12.4 sN/A
Memory usage79.5 GB19.7 GB
Memory %65%62%

HW Fit Score Breakdown

nemotron-3-super:latest

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

mistralai/devstral-smal…

Speed
25/50
TTFT
20/20
Memory
19/30

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

mistralai/devstral-smal…

Reasoning
17/20
Coding
16/20
Instruction
13/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

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