qwen3.6:35b-mlx
OLLAMA GGUFnvfp4
Jul 17, 2026 · Apple M5 Max
lfm2.5:latest
OLLAMA GGUFlfm2moe · 8.5B · Q4_K_M
Jun 11, 2026 · Intel Core™ i5-8350U
Global Score
80 vs 73
Hardware Fit
77 vs 93
Quality Score
81 vs 65
Hardware
qwen3.6:35b-mlx lfm2.5:latest
MachineMacBook ProLENOVO 20L7CTO1WW
CPUApple M5 MaxIntel Core™ i5-8350U
Cores188
RAM48 GB23 GB
GPUApple M5 MaxKaby Lake-R GT2 [UHD Graphics 620]
OSmacOS 26.5.2Fedora Linux 44
Archarm64x64
Power Modebalancedperformance
Performance
qwen3.6:35b-mlx lfm2.5:latest
Tokens/sec129.818.3
First chunk77 ms981 ms
TTFT30.0 s981 ms
Load time1.8 s8.0 s
Memory usage19.7 GB4.9 GB
Memory %41%21%
HW Fit Score Breakdown
qwen3.6:35b-mlx
Speed
50/50
TTFT
0/20
Memory
27/30
lfm2.5:latest
Speed
43/50
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
lfm2.5:latest
Reasoning
2/20
Coding
11/20
Instruction
14/20
Structured
13/15
Math
15/15
Multilingual
10/10
Reasoning: Poor Coding: Adequate Instruction Following: Adequate Structured Output: Strong 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