Back to leaderboard

llama3.1:8b

OLLAMA GGUF

llama · 8.0B · Q4_K_M

Marginal

Jun 26, 2026 · Cortex-A78AE

Qwen3.8-27B-UD-Q3_K_XL

OLLAMA GGUF

llama · 27.3B · Q4_K

Excellent

Aug 23, 2026 · Intel Gen Intel® Core™ i5-12600K

Global Score
46 vs 90
Hardware Fit
61 vs 97
Quality Score
40 vs 87

Hardware

llama3.1:8b Qwen3.8-27B-UD-Q3_…
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUCortex-A78AEIntel Gen Intel® Core™ i5-12600K
Cores616
RAM7 GB31 GB
GPUIntegrated / UnknownAlderLake-S GT1, AD106 [GeForce RTX 4060 Ti 16GB]
OSUbuntu 22.04.5 LTSUbuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedlow-power

Performance

llama3.1:8b Qwen3.8-27B-UD-Q3_…
Tokens/sec7.839.0
First chunk1625 ms305 ms
TTFT1.6 s305 ms
Load time21.8 s0.0 s
Memory usage5.2 GB12.5 GB
Memory %71%41%

HW Fit Score Breakdown

llama3.1:8b

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

Qwen3.8-27B-UD-Q3_K_XL

Speed
50/50
TTFT
20/20
Memory
27/30

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

Qwen3.8-27B-UD-Q3_K_XL

Reasoning
17/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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