Back to leaderboard

hf.co/unsloth/gemma-4-E2B-it-GGUF:UD-Q8_K_XL

OLLAMA GGUF

gemma4 · 4.65B · unknown

Excellent

Aug 23, 2026 · Apple M1 Pro

llama-3.1-8b-instruct

LM-STUDIO GGUF

llama · 8B · Q8_0

Excellent

Apr 26, 2026 · AMD Ryzen 5 5500

Global Score
84 vs 81
Hardware Fit
99 vs 100
Quality Score
77 vs 73

Hardware

hf.co/unsloth/gemm… llama-3.1-8b-instr…
MachineMacBook ProASUS
CPUApple M1 ProAMD Ryzen 5 5500
Cores1012
RAM16 GB31 GB
GPUApple M1 ProNavi 44 [Radeon RX 9060 XT]
OSmacOS 26.6.2Nobara Linux 43
Archarm64x64
Power Modebalancedperformance

Performance

hf.co/unsloth/gemm… llama-3.1-8b-instr…
Tokens/sec48.035.6
First chunk167 ms52 ms
TTFT167 ms256 ms
Load time4.7 sN/A
Memory usage5.3 GB8.6 GB
Memory %33%28%

HW Fit Score Breakdown

hf.co/unsloth/gemma-4-E…

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

llama-3.1-8b-instruct

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

Quality

hf.co/unsloth/gemma-4-E…

Reasoning
12/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

llama-3.1-8b-instruct

Reasoning
13/20
Coding
17/20
Instruction
13/20
Structured
15/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View hf.co/unsloth/gemm… details | View llama-3.1-8b-instr… 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