Back to leaderboard

llama3.3:70b-instruct-q4_K_M

OLLAMA GGUF

llama · 70.6B · Q4_K_M

Not Rec.

Aug 20, 2026 · Intel Xeon® E5-2637 v3

microsoft/phi-4-mini-reasoning

LM-STUDIO MLX

phi3 · 3.8B · 4bit

Good

Mar 3, 2026 · Apple M4

Global Score
51 vs 62
Hardware Fit
31 vs 99
Quality Score
60 vs 46

Hardware

llama3.3:70b-instr… microsoft/phi-4-mi…
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… microsoft/phi-4-mi…
Tokens/sec1.740.3
First chunk5553 ms289 ms
TTFT5.6 s289 ms
Load time0.4 sN/A
Memory usage50.3 GB2.0 GB
Memory %53%6%

HW Fit Score Breakdown

llama3.3:70b-instruct-q…

Speed
2/50
TTFT
5/20
Memory
24/30

microsoft/phi-4-mini-re…

Speed
50/50
TTFT
20/20
Memory
29/30

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

microsoft/phi-4-mini-re…

Reasoning
7/20
Coding
6/20
Instruction
7/20
Structured
7/15
Math
12/15
Multilingual
7/10
Reasoning: Weak Coding: Weak Instruction Following: Weak Structured Output: Weak Math: Strong Multilingual: Adequate

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest