Back to leaderboard

qwen2.5-coder:32b

OLLAMA GGUF

qwen2 · 32.8B · Q4_K_M

Good

Jun 26, 2026 · Cortex-X925

ministral-3:3b

OLLAMA GGUF

mistral3 · 3.8B · Q4_K_M

Good

Mar 6, 2026 · Apple M4

Global Score
78 vs 71
Hardware Fit
59 vs 99
Quality Score
86 vs 59

Hardware

qwen2.5-coder:32b ministral-3:3b
MachineNVIDIA NVIDIA_DGX_SparkMacBook Air
CPUCortex-X925Apple M4
Cores2010
RAM122 GB32 GB
GPUDevice 2e12Apple M4
OSUbuntu 24.04.4 LTSmacOS 26.3
Archarm64arm64
Power Modeperformancebalanced

Performance

qwen2.5-coder:32b ministral-3:3b
Tokens/sec9.542.2
First chunk394 ms189 ms
TTFT395 ms189 ms
Load time72.1 s1.2 s
Memory usage26.5 GB7.0 GB
Memory %22%22%

HW Fit Score Breakdown

qwen2.5-coder:32b

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

ministral-3:3b

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

Quality

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

ministral-3:3b

Reasoning
5/20
Coding
16/20
Instruction
11/20
Structured
14/15
Math
4/15
Multilingual
9/10
Reasoning: Weak 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