lfm2.5:latest
OLLAMA GGUFlfm2moe · 8.5B · Q4_K_M
Jun 11, 2026 · Intel Core™ i5-8350U
qwen3.5-0.8b-mlx
LM-STUDIO MLXqwen3_5 · 0.8B · 4bit
Mar 3, 2026 · Apple M4
Global Score
73 vs 55
Hardware Fit
93 vs 87
Quality Score
65 vs 41
Hardware
lfm2.5:latest qwen3.5-0.8b-mlx
MachineLENOVO 20L7CTO1WWMacBook Air
CPUIntel Core™ i5-8350UApple M4
Cores810
RAM23 GB32 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]Apple M4
OSFedora Linux 44macOS 26.3
Archx64arm64
Power Modeperformancebalanced
Performance
lfm2.5:latest qwen3.5-0.8b-mlx
Tokens/sec18.368.2
First chunk981 ms3268 ms
TTFT981 ms3.3 s
Load time8.0 sN/A
Memory usage4.9 GB0.6 GB
Memory %21%2%
HW Fit Score Breakdown
lfm2.5:latest
Speed
43/50
TTFT
20/20
Memory
30/30
qwen3.5-0.8b-mlx
Speed
50/50
TTFT
13/20
Memory
24/30
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
qwen3.5-0.8b-mlx
Reasoning
8/20
Coding
1/20
Instruction
12/20
Structured
12/15
Math
3/15
Multilingual
5/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
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