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

richardyoung/qwythos-9b-abliterated:Q8_0

OLLAMA GGUF

qwen35 · 9.0B · Q8_0

Good

Jun 28, 2026 · Apple M4 Pro

Global Score
84 vs 65
Hardware Fit
99 vs 96
Quality Score
77 vs 52

Hardware

hf.co/unsloth/gemm… richardyoung/qwyth…
MachineMacBook ProMac mini
CPUApple M1 ProApple M4 Pro
Cores1012
RAM16 GB24 GB
GPUApple M1 ProApple M4 Pro
OSmacOS 26.6.2macOS 15.6.1
Archarm64arm64
Power Modebalancedbalanced

Performance

hf.co/unsloth/gemm… richardyoung/qwyth…
Tokens/sec48.025.3
First chunk167 ms397 ms
TTFT167 ms397 ms
Load time4.7 s6.3 s
Memory usage5.3 GB8.3 GB
Memory %33%34%

HW Fit Score Breakdown

hf.co/unsloth/gemma-4-E…

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

richardyoung/qwythos-9b…

Speed
47/50
TTFT
20/20
Memory
29/30

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

richardyoung/qwythos-9b…

Reasoning
18/20
Coding
13/20
Instruction
6/20
Structured
0/15
Math
14/15
Multilingual
1/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Poor
View hf.co/unsloth/gemm… details | View richardyoung/qwyth… 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