Back to leaderboard

llama3.1:8b-instruct-q4_K_S

OLLAMA GGUF

llama · 8.0B · Q4_K_S

Good

Nov 22, 2026 · C1-Pro

qwen2.5:72b

OLLAMA GGUF

qwen2 · 72.7B · Q4_K_M

Not Rec.

Jun 27, 2026 · Cortex-X925

Global Score
70 vs 75
Hardware Fit
73 vs 50
Quality Score
68 vs 86

Hardware

llama3.1:8b-instru… qwen2.5:72b
Machine—NVIDIA NVIDIA_DGX_Spark
CPUC1-ProCortex-X925
Cores020
RAM11 GB122 GB
GPUIntegrated / UnknownDevice 2e12
OSunknown unknownUbuntu 24.04.4 LTS
Archarm64arm64
Power Modeunknownperformance

Performance

llama3.1:8b-instru… qwen2.5:72b
Tokens/sec6.54.4
First chunk950 ms529 ms
TTFT950 ms529 ms
Load time11.5 s49.7 s
Memory usage4.4 GB54.0 GB
Memory %38%44%

HW Fit Score Breakdown

llama3.1:8b-instruct-q4…

Speed
25/50
TTFT
20/20
Memory
28/30

qwen2.5:72b

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

Quality

llama3.1:8b-instruct-q4…

Reasoning
11/20
Coding
17/20
Instruction
11/20
Structured
14/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

qwen2.5:72b

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

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