qwen3.5:27b
OLLAMA GGUFqwen35 · 27.8B · Q4_K_M
Mar 10, 2026 · Apple M4
hf.co/LiquidAI/LFM2.5-2.6B-GGUF:F16
OLLAMA GGUFlfm2 · 2.7B · unknown
Aug 25, 2026 · Apple M1 Pro
Global Score
66 vs 61
Hardware Fit
34 vs 97
Quality Score
80 vs 46
Hardware
qwen3.5:27b hf.co/LiquidAI/LFM…
MachineMac miniMacBook Pro
CPUApple M4Apple M1 Pro
Cores1010
RAM24 GB16 GB
GPUApple M4Apple M1 Pro
OSmacOS 26.3macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.5:27b hf.co/LiquidAI/LFM…
Tokens/sec4.031.0
First chunk1655 ms129 ms
TTFT1.7 s129 ms
Load time12.9 s3.5 s
Memory usage21.3 GB6.6 GB
Memory %89%41%
HW Fit Score Breakdown
qwen3.5:27b
Speed
8/50
TTFT
20/20
Memory
6/30
hf.co/LiquidAI/LFM2.5-2…
Speed
50/50
TTFT
20/20
Memory
27/30
Quality
qwen3.5:27b
Reasoning
16/20
Coding
18/20
Instruction
9/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Strong Math: Strong Multilingual: Strong
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
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