llama3.3:70b
OLLAMA GGUFllama · 70.6B · Q4_K_M
Jun 26, 2026 · Cortex-X925
qwen3.6:35b
OLLAMA GGUFqwen35moe · 36.0B · Q4_K_M
May 25, 2026 · Apple M4 Pro
Global Score
73 vs 70
Hardware Fit
51 vs 66
Quality Score
83 vs 71
Hardware
llama3.3:70b qwen3.6:35b
MachineNVIDIA NVIDIA_DGX_SparkMacBook Pro
CPUCortex-X925Apple M4 Pro
Cores2014
RAM122 GB48 GB
GPUDevice 2e12Apple M4 Pro
OSUbuntu 24.04.4 LTSmacOS 26.4.1
Archarm64arm64
Power Modeperformancebalanced
Performance
llama3.3:70b qwen3.6:35b
Tokens/sec4.630.6
First chunk560 ms304 ms
TTFT560 ms30.0 s
Load time13.8 s10.0 s
Memory usage49.5 GB28.1 GB
Memory %41%59%
HW Fit Score Breakdown
llama3.3:70b
Speed
4/50
TTFT
20/20
Memory
27/30
qwen3.6:35b
Speed
45/50
TTFT
0/20
Memory
21/30
Quality
llama3.3:70b
Reasoning
17/20
Coding
18/20
Instruction
12/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
qwen3.6:35b
Reasoning
18/20
Coding
12/20
Instruction
12/20
Structured
6/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Adequate Structured Output: Weak 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