Back to leaderboard

richardyoung/qwythos-9b-abliterated:Q8_0

OLLAMA GGUF

qwen35 · 9.0B · Q8_0

Good

Jun 28, 2026 · Apple M4 Pro

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

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

Hardware

richardyoung/qwyth… hf.co/unsloth/gemm…
MachineMac miniMacBook Pro
CPUApple M4 ProApple M1 Pro
Cores1210
RAM24 GB16 GB
GPUApple M4 ProApple M1 Pro
OSmacOS 15.6.1macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced

Performance

richardyoung/qwyth… hf.co/unsloth/gemm…
Tokens/sec25.348.0
First chunk397 ms167 ms
TTFT397 ms167 ms
Load time6.3 s4.7 s
Memory usage8.3 GB5.3 GB
Memory %34%33%

HW Fit Score Breakdown

richardyoung/qwythos-9b…

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

hf.co/unsloth/gemma-4-E…

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

Quality

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

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
View richardyoung/qwyth… details | View hf.co/unsloth/gemm… 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