qwen3.6:35b-mlx
OLLAMA GGUFnvfp4
Jul 17, 2026 · Apple M5 Max
deepseek-r1:1.5b
OLLAMA GGUFqwen2 · 1.8B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
Global Score
80 vs 60
Hardware Fit
77 vs 90
Quality Score
81 vs 47
Hardware
qwen3.6:35b-mlx deepseek-r1:1.5b
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 deepseek-r1:1.5b
Tokens/sec129.834.6
First chunk77 ms5314 ms
TTFT30.0 s5.3 s
Load time1.8 s5.1 s
Memory usage19.7 GB1.1 GB
Memory %41%15%
HW Fit Score Breakdown
qwen3.6:35b-mlx
Speed
50/50
TTFT
0/20
Memory
27/30
deepseek-r1:1.5b
Speed
50/50
TTFT
10/20
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
deepseek-r1:1.5b
Reasoning
11/20
Coding
6/20
Instruction
7/20
Structured
4/15
Math
14/15
Multilingual
5/10
Reasoning: Adequate Coding: Weak Instruction Following: Weak Structured Output: Weak Math: Strong Multilingual: Weak
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