qwen3.5:latest
OLLAMA GGUFqwen35 · 9.7B · Q4_K_M
Mar 8, 2026 · Apple M4
hf.co/empero-ai/Qwen3.8-4B-Distill-GGUF:Q4_K_M
OLLAMA GGUFqwen35 · 4.33B · unknown
Aug 28, 2026 · Apple M4
Global Score
34 vs 66
Hardware Fit
58 vs 100
Quality Score
23 vs 52
Hardware
qwen3.5:latest hf.co/empero-ai/Qw…
MachineMac miniMacBook Pro
CPUApple M4Apple M4
Cores1010
RAM16 GB16 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.6.1
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.5:latest hf.co/empero-ai/Qw…
Tokens/sec13.326.5
First chunk438 ms447 ms
TTFT19.8 s447 ms
Load time0.2 s3.3 s
Memory usage8.0 GB4.8 GB
Memory %50%30%
HW Fit Score Breakdown
qwen3.5:latest
Speed
32/50
TTFT
1/20
Memory
25/30
hf.co/empero-ai/Qwen3.8…
Speed
50/50
TTFT
20/20
Memory
30/30
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
hf.co/empero-ai/Qwen3.8…
Reasoning
18/20
Coding
14/20
Instruction
4/20
Structured
1/15
Math
15/15
Multilingual
0/10
Reasoning: Strong Coding: Adequate Instruction Following: Poor 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