Back to leaderboard

gemma3:4b

OLLAMA GGUF

gemma3 · 4.3B · Q4_K_M

Good

Jun 26, 2026 · Cortex-A78AE

qwen3-next:80b-a3b-instruct-q4_K_M

OLLAMA GGUF

qwen3next · 79.7B · Q4_K_M

Not Rec.

Aug 23, 2026 · Intel Xeon® E5-4650 v2

Global Score
76 vs 74
Hardware Fit
92 vs 42
Quality Score
69 vs 87

Hardware

gemma3:4b qwen3-next:80b-a3b…
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperDell Inc. PowerEdge R820
CPUCortex-A78AEIntel Xeon® E5-4650 v2
Cores680
RAM7 GB256 GB
GPUIntegrated / UnknownMicrosoft Basic Display Adapter
OSUbuntu 22.04.5 LTSMicrosoft Windows Server 2022 Datacenter 10.0.20348
Archarm64x64
Power Modebalancedbalanced

Performance

gemma3:4b qwen3-next:80b-a3b…
Tokens/sec15.03.9
First chunk2380 ms2089 ms
TTFT2.4 s2.1 s
Load time13.6 s73.3 s
Memory usage2.6 GB46.9 GB
Memory %35%18%

HW Fit Score Breakdown

gemma3:4b

Speed
45/50
TTFT
18/20
Memory
29/30

qwen3-next:80b-a3b-inst…

Speed
3/50
TTFT
9/20
Memory
30/30

Quality

gemma3:4b

Reasoning
11/20
Coding
17/20
Instruction
13/20
Structured
14/15
Math
4/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

qwen3-next:80b-a3b-inst…

Reasoning
18/20
Coding
19/20
Instruction
12/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

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