llama3.3:70b-instruct-q4_K_M
OLLAMA GGUFllama · 70.6B · Q4_K_M
Aug 20, 2026 · Intel Xeon® E5-2637 v3
phi3:3.8b
OLLAMA GGUFphi3 · 3.8B · Q4_0
Mar 2, 2026 · Apple M4
Global Score
51 vs 64
Hardware Fit
31 vs 100
Quality Score
60 vs 48
Hardware
llama3.3:70b-instr… phi3:3.8b
MachineDell Inc. Precision Tower 7910MacBook Air
CPUIntel Xeon® E5-2637 v3Apple M4
Cores1610
RAM96 GB32 GB
GPUNVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060Apple M4
OSMicrosoft Windows 10 Pro 10.0.19045macOS 26.3
Archx64arm64
Power Modebalancedbalanced
Performance
llama3.3:70b-instr… phi3:3.8b
Tokens/sec1.742.0
First chunk5553 msN/A
TTFT5.6 s142 ms
Load time0.4 s1.1 s
Memory usage50.3 GB16.0 GB
Memory %53%50%
HW Fit Score Breakdown
llama3.3:70b-instruct-q…
Speed
2/50
TTFT
5/20
Memory
24/30
phi3:3.8b
Speed
40/50
TTFT
30/20
Memory
30/30
Quality
llama3.3:70b-instruct-q…
Reasoning
17/20
Coding
6/20
Instruction
6/20
Structured
11/15
Math
11/15
Multilingual
9/10
Reasoning: Strong Coding: Weak Instruction Following: Weak Structured Output: Adequate Math: Adequate Multilingual: Strong
phi3:3.8b
Reasoning
12/20
Coding
3/20
Instruction
11/20
Structured
10/15
Math
5/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Weak 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