Back to leaderboard

llama3.1:8b

OLLAMA GGUF

llama · 8.0B · Q4_K_M

Marginal

Jun 26, 2026 · Cortex-A78AE

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Good

Mar 7, 2026 · AMD Ryzen 5 5500

Global Score
46 vs 71
Hardware Fit
61 vs 56
Quality Score
40 vs 78

Hardware

llama3.1:8b qwen3.5:9b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperSystem manufacturer
CPUCortex-A78AEAMD Ryzen 5 5500
Cores612
RAM7 GB16 GB
GPUIntegrated / UnknownNVIDIA GeForce RTX 3060
OSUbuntu 22.04.5 LTSMicrosoft Windows 11 IoT Enterprise LTSC 10.0.26100
Archarm64x64
Power Modebalancedbalanced

Performance

llama3.1:8b qwen3.5:9b
Tokens/sec7.85.3
First chunk1625 ms1624 ms
TTFT1.6 s1.6 s
Load time21.8 s4.0 s
Memory usage5.2 GB7.9 GB
Memory %71%50%

HW Fit Score Breakdown

llama3.1:8b

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

qwen3.5:9b

Speed
11/50
TTFT
20/20
Memory
25/30

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

qwen3.5:9b

Reasoning
14/20
Coding
17/20
Instruction
12/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
View llama3.1:8b details | View qwen3.5:9b 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