qwen3.6:35b-mlx
OLLAMA GGUFnvfp4
Jul 17, 2026 · Apple M5 Max
mistral:latest
OLLAMA GGUFllama · 7.2B · Q4_K_M
May 27, 2026 · AMD Ryzen 5 2600X Six-Core Processor
Global Score
80 vs 73
Hardware Fit
77 vs 100
Quality Score
81 vs 62
Hardware
qwen3.6:35b-mlx mistral:latest
MachineMacBook ProMicro-Star International Co., Ltd. MS-7B79
CPUApple M5 MaxAMD Ryzen 5 2600X Six-Core Processor
Cores1812
RAM48 GB16 GB
GPUApple M5 MaxNVIDIA GeForce GTX 1080
OSmacOS 26.5.2Microsoft Windows 11 Famille 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
qwen3.6:35b-mlx mistral:latest
Tokens/sec129.831.7
First chunk77 ms102 ms
TTFT30.0 s102 ms
Load time1.8 s14.3 s
Memory usage19.7 GB4.8 GB
Memory %41%30%
HW Fit Score Breakdown
qwen3.6:35b-mlx
Speed
50/50
TTFT
0/20
Memory
27/30
mistral:latest
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
mistral:latest
Reasoning
8/20
Coding
13/20
Instruction
16/20
Structured
12/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak 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