qwen3.6:35b-mlx
OLLAMA GGUFnvfp4
Jul 17, 2026 · Apple M5 Max
llama3.1:8b
OLLAMA GGUFllama · 8.0B · Q4_K_M
Sep 15, 2026 · Intel Core™ i5-14400F
Global Score
80 vs 81
Hardware Fit
77 vs 100
Quality Score
81 vs 73
Hardware
qwen3.6:35b-mlx llama3.1:8b
MachineMacBook ProGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4
CPUApple M5 MaxIntel Core™ i5-14400F
Cores1816
RAM48 GB32 GB
GPUApple M5 MaxNVIDIA GeForce RTX 5060 Ti
OSmacOS 26.5.2Microsoft Windows 11 Professionnel 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
qwen3.6:35b-mlx llama3.1:8b
Tokens/sec129.870.2
First chunk77 ms58 ms
TTFT30.0 s58 ms
Load time1.8 s4.1 s
Memory usage19.7 GB4.9 GB
Memory %41%15%
HW Fit Score Breakdown
qwen3.6:35b-mlx
Speed
50/50
TTFT
0/20
Memory
27/30
llama3.1:8b
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
llama3.1:8b
Reasoning
12/20
Coding
18/20
Instruction
15/20
Structured
13/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong 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