qwen3.6:35b-mlx
OLLAMA GGUFnvfp4
Jul 17, 2026 · Apple M5 Max
llama3.2:1b
OLLAMA GGUFllama · 1.2B · Q8_0
Jun 26, 2026 · Cortex-A78AE
Global Score
80 vs 63
Hardware Fit
77 vs 100
Quality Score
81 vs 47
Hardware
qwen3.6:35b-mlx llama3.2:1b
MachineMacBook ProNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUApple M5 MaxCortex-A78AE
Cores186
RAM48 GB7 GB
GPUApple M5 MaxIntegrated / Unknown
OSmacOS 26.5.2Ubuntu 22.04.5 LTS
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.6:35b-mlx llama3.2:1b
Tokens/sec129.840.2
First chunk77 ms1087 ms
TTFT30.0 s1.1 s
Load time1.8 s6.2 s
Memory usage19.7 GB1.4 GB
Memory %41%19%
HW Fit Score Breakdown
qwen3.6:35b-mlx
Speed
50/50
TTFT
0/20
Memory
27/30
llama3.2:1b
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
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
llama3.2:1b
Reasoning
4/20
Coding
9/20
Instruction
14/20
Structured
13/15
Math
1/15
Multilingual
6/10
Reasoning: Poor Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
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