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

llama3.2:1b

OLLAMA GGUF

llama · 1.2B · Q8_0

Good

Jun 26, 2026 · Cortex-A78AE

Global Score
84 vs 63
Hardware Fit
99 vs 100
Quality Score
77 vs 47

Hardware

hf.co/unsloth/gemm… llama3.2:1b
MachineMacBook ProNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUApple M1 ProCortex-A78AE
Cores106
RAM16 GB7 GB
GPUApple M1 ProIntegrated / Unknown
OSmacOS 26.6.2Ubuntu 22.04.5 LTS
Archarm64arm64
Power Modebalancedbalanced

Performance

hf.co/unsloth/gemm… llama3.2:1b
Tokens/sec48.040.2
First chunk167 ms1087 ms
TTFT167 ms1.1 s
Load time4.7 s6.2 s
Memory usage5.3 GB1.4 GB
Memory %33%19%

HW Fit Score Breakdown

hf.co/unsloth/gemma-4-E…

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

llama3.2:1b

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

llama3.2:1b

Reasoning
4/20
Coding
9/20
Instruction
14/20
Structured
13/15
Math
1/15
Multilingual
6/10
Reasoning: Poor Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
View hf.co/unsloth/gemm… details | View llama3.2:1b 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