starcoder2:3b
OLLAMA GGUFstarcoder2 · 3B · Q4_0
Jun 26, 2026 · Cortex-A78AE
hf.co/lmstudio-community/gemma-4-E4B-it-GGUF:Q6_K
OLLAMA GGUFgemma4 · 7.52B · unknown
Aug 23, 2026 · Apple M1 Pro
Global Score
35 vs 88
Hardware Fit
100 vs 100
Quality Score
7 vs 83
Hardware
starcoder2:3b hf.co/lmstudio-com…
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperMacBook Pro
CPUCortex-A78AEApple M1 Pro
Cores610
RAM7 GB16 GB
GPUIntegrated / UnknownApple M1 Pro
OSUbuntu 22.04.5 LTSmacOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
starcoder2:3b hf.co/lmstudio-com…
Tokens/sec31.534.6
First chunk392 ms210 ms
TTFT392 ms210 ms
Load time4.8 s4.0 s
Memory usage1.8 GB3.9 GB
Memory %24%25%
HW Fit Score Breakdown
starcoder2:3b
Speed
50/50
TTFT
20/20
Memory
30/30
hf.co/lmstudio-communit…
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
starcoder2:3b
Reasoning
0/20
Coding
3/20
Instruction
1/20
Structured
0/15
Math
1/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
hf.co/lmstudio-communit…
Reasoning
14/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
9/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
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