qwen3.5:latest
OLLAMA GGUFqwen35 · 9.7B · Q4_K_M
Mar 8, 2026 · Apple M4
richardyoung/qwythos-9b-abliterated:Q8_0
OLLAMA GGUFqwen35 · 9.0B · Q8_0
Jun 28, 2026 · Apple M4 Pro
Global Score
34 vs 65
Hardware Fit
58 vs 96
Quality Score
23 vs 52
Hardware
qwen3.5:latest richardyoung/qwyth…
MachineMac miniMac mini
CPUApple M4Apple M4 Pro
Cores1012
RAM16 GB24 GB
GPUApple M4Apple M4 Pro
OSmacOS 26.3macOS 15.6.1
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.5:latest richardyoung/qwyth…
Tokens/sec13.325.3
First chunk438 ms397 ms
TTFT19.8 s397 ms
Load time0.2 s6.3 s
Memory usage8.0 GB8.3 GB
Memory %50%34%
HW Fit Score Breakdown
qwen3.5:latest
Speed
32/50
TTFT
1/20
Memory
25/30
richardyoung/qwythos-9b…
Speed
47/50
TTFT
20/20
Memory
29/30
Quality
qwen3.5:latest
Reasoning
6/20
Coding
1/20
Instruction
3/20
Structured
0/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Weak 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
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