qwen3.5:0.8b
OLLAMA GGUFqwen35 · 873.44M · Q8_0
Mar 5, 2026 · Apple M1 Max
deepseek-r1:latest
OLLAMA GGUFqwen2 · 7.6B · Q4_K_M
Jun 25, 2026 · Cortex-A78AE
Global Score
62 vs 23
Hardware Fit
100 vs 70
Quality Score
46 vs 3
Hardware
qwen3.5:0.8b 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
qwen3.5:0.8b deepseek-r1:latest
Tokens/sec67.69.8
First chunk209 ms1206 ms
TTFT209 ms1.2 s
Load time1.9 s17.8 s
Memory usage2.6 GB4.8 GB
Memory %8%65%
HW Fit Score Breakdown
qwen3.5:0.8b
Speed
50/50
TTFT
20/20
Memory
30/30
deepseek-r1:latest
Speed
32/50
TTFT
20/20
Memory
18/30
Quality
qwen3.5:0.8b
Reasoning
9/20
Coding
4/20
Instruction
11/20
Structured
13/15
Math
3/15
Multilingual
6/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
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
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