Back to leaderboard

qwen3:4b

OLLAMA GGUF

qwen3 · 4.0B · Q4_K_M

Not Rec.

Jun 26, 2026 · Cortex-A78AE

qwen2.5-coder:7b

OLLAMA GGUF

qwen2 · 7.6B · Q4_K_M

Good

Mar 5, 2026 · Intel Gen Intel® Core™ i7-13700K

Global Score
32 vs 68
Hardware Fit
98 vs 59
Quality Score
4 vs 72

Hardware

qwen3:4b qwen2.5-coder:7b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperASUS
CPUCortex-A78AEIntel Gen Intel® Core™ i7-13700K
Cores624
RAM7 GB64 GB
GPUIntegrated / UnknownNVIDIA GeForce RTX 3070
OSUbuntu 22.04.5 LTSMicrosoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedunknown

Performance

qwen3:4b qwen2.5-coder:7b
Tokens/sec17.934.4
First chunk950 ms1991 ms
TTFT950 ms2.0 s
Load time9.7 s40.6 s
Memory usage3.0 GB5.0 GB
Memory %40%8%

HW Fit Score Breakdown

qwen3:4b

Speed
50/50
TTFT
20/20
Memory
28/30

qwen2.5-coder:7b

Speed
38/50
TTFT
12/20
Memory
9/30

Quality

qwen3:4b

Reasoning
4/20
Coding
0/20
Instruction
0/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

qwen2.5-coder:7b

Reasoning
11/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
9/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3:4b details | View qwen2.5-coder:7b 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