Back to leaderboard

nemotron-3-nano:4b

OLLAMA GGUF

nemotron_h · 4.0B · Q4_K_M

Excellent

Aug 26, 2026 · Apple M1 Pro

qwen2.5-coder:32b

OLLAMA GGUF

qwen2 · 32.8B · Q4_K_M

Good

Jun 26, 2026 · Cortex-X925

Global Score
93 vs 78
Hardware Fit
95 vs 59
Quality Score
92 vs 86

Hardware

nemotron-3-nano:4b qwen2.5-coder:32b
MachineMacBook ProNVIDIA NVIDIA_DGX_Spark
CPUApple M1 ProCortex-X925
Cores1020
RAM16 GB122 GB
GPUApple M1 ProDevice 2e12
OSmacOS 26.6.2Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance

Performance

nemotron-3-nano:4b qwen2.5-coder:32b
Tokens/sec31.79.5
First chunk270 ms394 ms
TTFT2.9 s395 ms
Load time2.1 s72.1 s
Memory usage4.1 GB26.5 GB
Memory %25%22%

HW Fit Score Breakdown

nemotron-3-nano:4b

Speed
50/50
TTFT
15/20
Memory
30/30

qwen2.5-coder:32b

Speed
9/50
TTFT
20/20
Memory
30/30

Quality

nemotron-3-nano:4b

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

qwen2.5-coder:32b

Reasoning
14/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View nemotron-3-nano:4b details | View qwen2.5-coder:32b 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