Back to leaderboard

qwen2.5-coder:32b

OLLAMA GGUF

qwen2 · 32.8B · Q4_K_M

Good

Jun 26, 2026 · Cortex-X925

rnj-1:8b

OLLAMA GGUF

gemma3 · 8.3B · Q4_K_M

Excellent

Aug 24, 2026 · Apple M1 Pro

Global Score
78 vs 80
Hardware Fit
59 vs 93
Quality Score
86 vs 74

Hardware

qwen2.5-coder:32b rnj-1:8b
MachineNVIDIA NVIDIA_DGX_SparkMacBook Pro
CPUCortex-X925Apple M1 Pro
Cores2010
RAM122 GB16 GB
GPUDevice 2e12Apple M1 Pro
OSUbuntu 24.04.4 LTSmacOS 26.6.2
Archarm64arm64
Power Modeperformancebalanced

Performance

qwen2.5-coder:32b rnj-1:8b
Tokens/sec9.522.3
First chunk394 ms404 ms
TTFT395 ms404 ms
Load time72.1 s3.7 s
Memory usage26.5 GB8.3 GB
Memory %22%52%

HW Fit Score Breakdown

qwen2.5-coder:32b

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

rnj-1:8b

Speed
49/50
TTFT
20/20
Memory
24/30

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

rnj-1:8b

Reasoning
12/20
Coding
19/20
Instruction
15/20
Structured
5/15
Math
14/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Weak Math: Strong Multilingual: Strong
View qwen2.5-coder:32b details | View rnj-1:8b 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