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

qwen2.5-1.5b-instruct

LM-STUDIO GGUF

qwen2 · 1.5B · Q4_K_M

Good

Mar 6, 2026 · Intel Core™ i5-5300U

Global Score
80 vs 61
Hardware Fit
100 vs 69
Quality Score
71 vs 58

Hardware

gemma-3-4b-it-q4-k-m qwen2.5-1.5b-instr…
MachineMac ProLENOVO 20BUS00700
CPUIntel Core™ i5-10400Intel Core™ i5-5300U
Cores124
RAM32 GB16 GB
GPUAMD Radeon RX 6700 XTIntel(R) HD Graphics 5500
OSmacOS 26.5.1Microsoft Windows 10 Professionnel 10.0.19045
Archx64x64
Power Modebalancedbalanced

Performance

gemma-3-4b-it-q4-k-m qwen2.5-1.5b-instr…
Tokens/sec75.06.6
First chunk136 ms2277 ms
TTFT136 ms2.3 s
Load time0.0 sN/A
Memory usage0.8 GB0.9 GB
Memory %3%6%

HW Fit Score Breakdown

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

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

qwen2.5-1.5b-instruct

Speed
23/50
TTFT
19/20
Memory
27/30

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

qwen2.5-1.5b-instruct

Reasoning
9/20
Coding
9/20
Instruction
13/20
Structured
14/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View gemma-3-4b-it-q4-k-m details | View qwen2.5-1.5b-instr… 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