richardyoung/qwythos-9b-abliterated:Q8_0
OLLAMA GGUFqwen35 · 9.0B · Q8_0
Jun 28, 2026 · Apple M4 Pro
devstral-small-2-24b-instruct-2512
LM-STUDIO GGUFmistral3 · 24B · IQ4_XS
Sep 20, 2026 · AMD Ryzen 7 5800X 8-Core Processor
Global Score
65 vs 81
Hardware Fit
96 vs 80
Quality Score
52 vs 81
Hardware
richardyoung/qwyth… devstral-small-2-2…
MachineMac miniSystem manufacturer
CPUApple M4 ProAMD Ryzen 7 5800X 8-Core Processor
Cores1216
RAM24 GB31 GB
GPUApple M4 ProNavi 44 [Radeon RX 9060 XT]
OSmacOS 15.6.1Ubuntu 26.04.1 LTS
Archarm64x64
Power Modebalancedperformance
Performance
richardyoung/qwyth… devstral-small-2-2…
Tokens/sec25.321.5
First chunk397 ms12 ms
TTFT397 ms212 ms
Load time6.3 sN/A
Memory usage8.3 GB15.9 GB
Memory %34%51%
HW Fit Score Breakdown
richardyoung/qwythos-9b…
Speed
47/50
TTFT
20/20
Memory
29/30
devstral-small-2-24b-in…
Speed
35/50
TTFT
20/20
Memory
25/30
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
devstral-small-2-24b-in…
Reasoning
16/20
Coding
17/20
Instruction
17/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest