qwen2.5:3b
OLLAMA GGUFqwen2 · 3.1B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
qwen3.5:0.8b
OLLAMA GGUFqwen35 · 873.44M · Q8_0
Mar 5, 2026 · Apple M1 Max
Global Score
77 vs 62
Hardware Fit
100 vs 100
Quality Score
67 vs 46
Hardware
qwen2.5:3b qwen3.5:0.8b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperMacBook Pro
CPUCortex-A78AEApple M1 Max
Cores610
RAM7 GB32 GB
GPUIntegrated / UnknownApple M1 Max
OSUbuntu 22.04.5 LTSmacOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen2.5:3b qwen3.5:0.8b
Tokens/sec21.465.8
First chunk1006 ms230 ms
TTFT1.0 s230 ms
Load time6.4 s1.5 s
Memory usage2.0 GB2.6 GB
Memory %27%8%
HW Fit Score Breakdown
qwen2.5:3b
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3.5:0.8b
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
qwen2.5:3b
Reasoning
12/20
Coding
14/20
Instruction
11/20
Structured
15/15
Math
6/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
qwen3.5:0.8b
Reasoning
9/20
Coding
4/20
Instruction
11/20
Structured
13/15
Math
3/15
Multilingual
6/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest