hf.co/LiquidAI/LFM2.5-2.6B-GGUF:F16
OLLAMA GGUFlfm2 · 2.7B · unknown
Aug 25, 2026 · Apple M1 Pro
qwen3:8b
OLLAMA GGUFqwen3 · 8.2B · Q4_K_M
Apr 28, 2026 · Intel Xeon® Gold 6230
Global Score
61 vs 80
Hardware Fit
97 vs 85
Quality Score
46 vs 78
Hardware
hf.co/LiquidAI/LFM… qwen3:8b
MachineMacBook ProHP HP Z8 G4 Workstation
CPUApple M1 ProIntel Xeon® Gold 6230
Cores1080
RAM16 GB252 GB
GPUApple M1 ProTU104GL [Quadro RTX 5000]
OSmacOS 26.6.2Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedlow-power
Performance
hf.co/LiquidAI/LFM… qwen3:8b
Tokens/sec31.065.1
First chunk129 ms289 ms
TTFT129 ms4.2 s
Load time3.5 s4.6 s
Memory usage6.6 GB5.6 GB
Memory %41%2%
HW Fit Score Breakdown
hf.co/LiquidAI/LFM2.5-2…
Speed
50/50
TTFT
20/20
Memory
27/30
qwen3:8b
Speed
50/50
TTFT
5/20
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
qwen3:8b
Reasoning
17/20
Coding
10/20
Instruction
14/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong 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