Back to leaderboard

qwen3:4b

OLLAMA GGUF

qwen3 · 4.0B · Q4_K_M

Not Rec.

Nov 4, 2026 · Intel Core™ i7-9700

qwen2.5:72b

OLLAMA GGUF

qwen2 · 72.7B · Q4_K_M

Not Rec.

Jun 27, 2026 · Cortex-X925

Global Score
29 vs 75
Hardware Fit
84 vs 50
Quality Score
6 vs 86

Hardware

qwen3:4b qwen2.5:72b
MachineVMware, Inc. VMware Virtual PlatformNVIDIA NVIDIA_DGX_Spark
CPUIntel Core™ i7-9700Cortex-X925
Cores420
RAM16 GB122 GB
GPUIntegrated / UnknownDevice 2e12
OSUbuntu 24.04.5 LTSUbuntu 24.04.4 LTS
Archx64arm64
Power Modeunknownperformance

Performance

qwen3:4b qwen2.5:72b
Tokens/sec10.44.4
First chunk857 ms529 ms
TTFT857 ms529 ms
Load time41.0 s49.7 s
Memory usage3.0 GB54.0 GB
Memory %19%44%

HW Fit Score Breakdown

qwen3:4b

Speed
34/50
TTFT
20/20
Memory
30/30

qwen2.5:72b

Speed
4/50
TTFT
20/20
Memory
26/30

Quality

qwen3:4b

Reasoning
0/20
Coding
2/20
Instruction
2/20
Structured
0/15
Math
1/15
Multilingual
1/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

qwen2.5:72b

Reasoning
19/20
Coding
19/20
Instruction
12/20
Structured
14/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3:4b details | View qwen2.5:72b 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