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

ministral-3:8b

OLLAMA GGUF

mistral3 · 8.9B · Q4_K_M

Good

Aug 25, 2026 · Apple M1 Pro

Global Score
51 vs 72
Hardware Fit
31 vs 71
Quality Score
60 vs 72

Hardware

llama3.3:70b-instr… ministral-3:8b
MachineDell Inc. Precision Tower 7910MacBook Pro
CPUIntel Xeon® E5-2637 v3Apple M1 Pro
Cores1610
RAM96 GB16 GB
GPUNVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060Apple M1 Pro
OSMicrosoft Windows 10 Pro 10.0.19045macOS 26.6.2
Archx64arm64
Power Modebalancedbalanced

Performance

llama3.3:70b-instr… ministral-3:8b
Tokens/sec1.719.8
First chunk5553 ms269 ms
TTFT5.6 s269 ms
Load time0.4 s10.7 s
Memory usage50.3 GB13.7 GB
Memory %53%86%

HW Fit Score Breakdown

llama3.3:70b-instruct-q…

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

ministral-3:8b

Speed
44/50
TTFT
20/20
Memory
7/30

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

ministral-3:8b

Reasoning
12/20
Coding
18/20
Instruction
13/20
Structured
13/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

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