hf.co/LiquidAI/LFM2.5-2.6B-GGUF:F16
OLLAMA GGUFlfm2 · 2.7B · unknown
Aug 25, 2026 · Apple M1 Pro
qwen2.5:1.5b
OLLAMA GGUFqwen2 · 1.5B · Q4_K_M
Jun 17, 2026 · ZHAOXIN KaiXian KX-7000 KaiXian KX-7000
Global Score
61 vs 65
Hardware Fit
97 vs 87
Quality Score
46 vs 56
Hardware
hf.co/LiquidAI/LFM… qwen2.5:1.5b
MachineMacBook ProShanghai Zhaoxin Semiconductor Co., Ltd. ZXE CRB
CPUApple M1 ProZHAOXIN KaiXian KX-7000 KaiXian KX-7000
Cores108
RAM16 GB30 GB
GPUApple M1 ProZX C-1190
OSmacOS 26.6.2Microsoft Windows 11 Pro 10.0.26100
Archarm64x64
Power Modebalancedbalanced
Performance
hf.co/LiquidAI/LFM… qwen2.5:1.5b
Tokens/sec31.016.8
First chunk129 ms941 ms
TTFT129 ms941 ms
Load time3.5 s0.2 s
Memory usage6.6 GB1.0 GB
Memory %41%3%
HW Fit Score Breakdown
hf.co/LiquidAI/LFM2.5-2…
Speed
50/50
TTFT
20/20
Memory
27/30
qwen2.5:1.5b
Speed
37/50
TTFT
20/20
Memory
30/30
Quality
hf.co/LiquidAI/LFM2.5-2…
Reasoning
14/20
Coding
13/20
Instruction
3/20
Structured
0/15
Math
14/15
Multilingual
2/10
Reasoning: Adequate Coding: Adequate Instruction Following: Poor Structured Output: Poor Math: Strong Multilingual: Poor
qwen2.5:1.5b
Reasoning
8/20
Coding
10/20
Instruction
12/20
Structured
13/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate 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