qwen2.5-coder:32b
OLLAMA GGUFqwen2 · 32.8B · Q4_K_M
Jun 26, 2026 · Cortex-X925
hf.co/LiquidAI/LFM2.5-2.6B-GGUF:F16
OLLAMA GGUFlfm2 · 2.7B · unknown
Aug 23, 2026 · Apple M1 Pro
Global Score
78 vs 61
Hardware Fit
59 vs 97
Quality Score
86 vs 46
Hardware
qwen2.5-coder:32b hf.co/LiquidAI/LFM…
MachineNVIDIA NVIDIA_DGX_SparkMacBook Pro
CPUCortex-X925Apple M1 Pro
Cores2010
RAM122 GB16 GB
GPUDevice 2e12Apple M1 Pro
OSUbuntu 24.04.4 LTSmacOS 26.6.2
Archarm64arm64
Power Modeperformancebalanced
Performance
qwen2.5-coder:32b hf.co/LiquidAI/LFM…
Tokens/sec9.531.4
First chunk394 ms138 ms
TTFT395 ms138 ms
Load time72.1 s3.7 s
Memory usage26.5 GB6.6 GB
Memory %22%41%
HW Fit Score Breakdown
qwen2.5-coder:32b
Speed
9/50
TTFT
20/20
Memory
30/30
hf.co/LiquidAI/LFM2.5-2…
Speed
50/50
TTFT
20/20
Memory
27/30
Quality
qwen2.5-coder:32b
Reasoning
14/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong 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