Back to leaderboard

llama3.1:8b

OLLAMA GGUF

llama · 8.0B · Q4_K_M

Marginal

Jun 26, 2026 · Cortex-A78AE

qwen2-57b:57B

OLLAMA GGUF

qwen2moe · 57.4B · Q4_K_M

Good

Aug 18, 2026 · Intel Core™ Ultra X7 358H

Global Score
46 vs 67
Hardware Fit
61 vs 51
Quality Score
40 vs 74

Hardware

llama3.1:8b qwen2-57b:57B
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperGMKtec NucBox EVO-T2S
CPUCortex-A78AEIntel Core™ Ultra X7 358H
Cores616
RAM7 GB64 GB
GPUIntegrated / UnknownIntel(R) Arc(TM) B390 GPU
OSUbuntu 22.04.5 LTSMicrosoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

llama3.1:8b qwen2-57b:57B
Tokens/sec7.88.6
First chunk1625 ms1573 ms
TTFT1.6 s1.6 s
Load time21.8 s29.0 s
Memory usage5.2 GB32.8 GB
Memory %71%52%

HW Fit Score Breakdown

llama3.1:8b

Speed
26/50
TTFT
20/20
Memory
15/30

qwen2-57b:57B

Speed
10/50
TTFT
17/20
Memory
24/30

Quality

llama3.1:8b

Reasoning
12/20
Coding
10/20
Instruction
4/20
Structured
1/15
Math
4/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Poor Structured Output: Poor Math: Weak Multilingual: Strong

qwen2-57b:57B

Reasoning
13/20
Coding
14/20
Instruction
15/20
Structured
14/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Adequate 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