qwen3.5:4b
OLLAMA GGUFqwen35 · 4.7B · Q4_K_M
Mar 5, 2026 · Apple M1 Max
deepseek-r1:latest
OLLAMA GGUFqwen2 · 7.6B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
Global Score
83 vs 22
Hardware Fit
100 vs 69
Quality Score
76 vs 2
Hardware
qwen3.5:4b deepseek-r1:latest
MachineMacBook ProNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUApple M1 MaxCortex-A78AE
Cores106
RAM32 GB7 GB
GPUApple M1 MaxIntegrated / Unknown
OSmacOS 26.3Ubuntu 22.04.5 LTS
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.5:4b deepseek-r1:latest
Tokens/sec32.49.6
First chunk306 ms1300 ms
TTFT306 ms1.3 s
Load time2.7 s19.9 s
Memory usage6.5 GB4.8 GB
Memory %20%65%
HW Fit Score Breakdown
qwen3.5:4b
Speed
50/50
TTFT
20/20
Memory
30/30
deepseek-r1:latest
Speed
31/50
TTFT
20/20
Memory
18/30
Quality
qwen3.5:4b
Reasoning
16/20
Coding
14/20
Instruction
15/20
Structured
15/15
Math
7/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
deepseek-r1:latest
Reasoning
0/20
Coding
1/20
Instruction
0/20
Structured
0/15
Math
1/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor 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