deepseek-r1:latest
OLLAMA GGUFqwen2 · 7.6B · Q4_K_M
Jun 25, 2026 · Cortex-A78AE
qwen3.5:27b
OLLAMA GGUFqwen35 · 27.8B · Q4_K_M
Mar 19, 2026 · Apple M4
Global Score
23 vs 66
Hardware Fit
70 vs 34
Quality Score
3 vs 79
Hardware
deepseek-r1:latest qwen3.5:27b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperMac mini
CPUCortex-A78AEApple M4
Cores610
RAM7 GB24 GB
GPUIntegrated / UnknownApple M4
OSUbuntu 22.04.5 LTSmacOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
deepseek-r1:latest qwen3.5:27b
Tokens/sec9.83.8
First chunk1206 ms1637 ms
TTFT1.2 s1.6 s
Load time17.8 s17.0 s
Memory usage4.8 GB21.3 GB
Memory %65%89%
HW Fit Score Breakdown
deepseek-r1:latest
Speed
32/50
TTFT
20/20
Memory
18/30
qwen3.5:27b
Speed
8/50
TTFT
20/20
Memory
6/30
Quality
deepseek-r1:latest
Reasoning
0/20
Coding
1/20
Instruction
0/20
Structured
0/15
Math
2/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
qwen3.5:27b
Reasoning
16/20
Coding
18/20
Instruction
8/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Weak 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