Back to leaderboard

gemma-3-4b-it-q4-k-m

OLLAMA GGUF

llama · 4B · Q4_K_M

Excellent

Jul 9, 2026 · Intel Core™ i5-10400

starcoder2:3b

OLLAMA GGUF

starcoder2 · 3B · Q4_0

Not Rec.

Jun 26, 2026 · Cortex-A78AE

Global Score
80 vs 35
Hardware Fit
100 vs 100
Quality Score
71 vs 7

Hardware

gemma-3-4b-it-q4-k-m starcoder2:3b
MachineMac ProNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUIntel Core™ i5-10400Cortex-A78AE
Cores126
RAM32 GB7 GB
GPUAMD Radeon RX 6700 XTIntegrated / Unknown
OSmacOS 26.5.1Ubuntu 22.04.5 LTS
Archx64arm64
Power Modebalancedbalanced

Performance

gemma-3-4b-it-q4-k-m starcoder2:3b
Tokens/sec75.031.5
First chunk136 ms392 ms
TTFT136 ms392 ms
Load time0.0 s4.8 s
Memory usage0.8 GB1.8 GB
Memory %3%24%

HW Fit Score Breakdown

gemma-3-4b-it-q4-k-m

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

starcoder2:3b

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

Quality

gemma-3-4b-it-q4-k-m

Reasoning
11/20
Coding
17/20
Instruction
14/20
Structured
14/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

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

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