llama3.2:1b
OLLAMA GGUFllama · 1.2B · Q8_0
Jun 26, 2026 · Cortex-A78AE
qwen3.5-27b-claude-4.6-opus-distilled-mlx
LM-STUDIO MLXqwen3_5 · 27B · 4bit
Mar 10, 2026 · Apple M4
Global Score
63 vs 34
Hardware Fit
100 vs 21
Quality Score
47 vs 39
Hardware
llama3.2:1b qwen3.5-27b-claude…
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
llama3.2:1b qwen3.5-27b-claude…
Tokens/sec40.26.1
First chunk1087 ms7 ms
TTFT1.1 s22.9 s
Load time6.2 sN/A
Memory usage1.4 GB19.8 GB
Memory %19%82%
HW Fit Score Breakdown
llama3.2:1b
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3.5-27b-claude-4.6-…
Speed
12/50
TTFT
0/20
Memory
9/30
Quality
llama3.2:1b
Reasoning
4/20
Coding
9/20
Instruction
14/20
Structured
13/15
Math
1/15
Multilingual
6/10
Reasoning: Poor Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
qwen3.5-27b-claude-4.6-…
Reasoning
1/20
Coding
14/20
Instruction
5/20
Structured
8/15
Math
4/15
Multilingual
7/10
Reasoning: Poor Coding: Adequate Instruction Following: Weak Structured Output: Adequate Math: Poor Multilingual: Adequate
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