hf.co/Edge-Quant/Nanbeige4.1-3B-Q8_0-GGUF:Q8_0
OLLAMA GGUFllama · 3.93B · unknown
Aug 22, 2026 · Apple M1 Pro
qwen3.6:35b-mlx
OLLAMA GGUFnvfp4
Jul 17, 2026 · Apple M5 Max
Global Score
52 vs 80
Hardware Fit
75 vs 77
Quality Score
42 vs 81
Hardware
hf.co/Edge-Quant/N… qwen3.6:35b-mlx
MachineMacBook ProMacBook Pro
CPUApple M1 ProApple M5 Max
Cores1018
RAM16 GB48 GB
GPUApple M1 ProApple M5 Max
OSmacOS 26.6.2macOS 26.5.2
Archarm64arm64
Power Modebalancedbalanced
Performance
hf.co/Edge-Quant/N… qwen3.6:35b-mlx
Tokens/sec43.5129.8
First chunk225 ms77 ms
TTFT30.0 s30.0 s
Load time2.7 s1.8 s
Memory usage8.2 GB19.7 GB
Memory %51%41%
HW Fit Score Breakdown
hf.co/Edge-Quant/Nanbei…
Speed
50/50
TTFT
0/20
Memory
25/30
qwen3.6:35b-mlx
Speed
50/50
TTFT
0/20
Memory
27/30
Quality
hf.co/Edge-Quant/Nanbei…
Reasoning
13/20
Coding
1/20
Instruction
7/20
Structured
1/15
Math
13/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Adequate
qwen3.6:35b-mlx
Reasoning
19/20
Coding
9/20
Instruction
18/20
Structured
11/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Strong Structured Output: Adequate Math: Strong 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