lfm2.5:latest
OLLAMA GGUFlfm2moe · 8.5B · Q4_K_M
Jun 11, 2026 · Intel Core™ i5-8350U
qwen/qwen3.6-35b-a3b
LM-STUDIO MLXqwen3_5_moe · 35B · 4bit
Jul 17, 2026 · Apple M5 Max
Global Score
73 vs 89
Hardware Fit
93 vs 97
Quality Score
65 vs 86
Hardware
lfm2.5:latest qwen/qwen3.6-35b-a3b
MachineLENOVO 20L7CTO1WWMacBook Pro
CPUIntel Core™ i5-8350UApple M5 Max
Cores818
RAM23 GB64 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]Apple M5 Max
OSFedora Linux 44macOS 27.0
Archx64arm64
Power Modeperformancebalanced
Performance
lfm2.5:latest qwen/qwen3.6-35b-a3b
Tokens/sec18.3130.2
First chunk981 ms5 ms
TTFT981 ms135 ms
Load time8.0 sN/A
Memory usage4.9 GB26.6 GB
Memory %21%42%
HW Fit Score Breakdown
lfm2.5:latest
Speed
43/50
TTFT
20/20
Memory
30/30
qwen/qwen3.6-35b-a3b
Speed
50/50
TTFT
20/20
Memory
27/30
Quality
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
qwen/qwen3.6-35b-a3b
Reasoning
15/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong 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