Back to leaderboard

llama3.3:70b

OLLAMA GGUF

llama · 70.6B · Q4_K_M

Not Rec.

Jun 26, 2026 · Cortex-X925

mistralai/magistral-small-2509

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Mar 4, 2026 · Apple M4

Global Score
73 vs 74
Hardware Fit
51 vs 66
Quality Score
83 vs 78

Hardware

llama3.3:70b mistralai/magistra…
MachineNVIDIA NVIDIA_DGX_SparkMacBook Air
CPUCortex-X925Apple M4
Cores2010
RAM122 GB32 GB
GPUDevice 2e12Apple M4
OSUbuntu 24.04.4 LTSmacOS 26.3
Archarm64arm64
Power Modeperformancebalanced

Performance

llama3.3:70b mistralai/magistra…
Tokens/sec4.67.9
First chunk560 ms1356 ms
TTFT560 ms1.4 s
Load time13.8 sN/A
Memory usage49.5 GB13.2 GB
Memory %41%41%

HW Fit Score Breakdown

llama3.3:70b

Speed
4/50
TTFT
20/20
Memory
27/30

mistralai/magistral-sma…

Speed
16/50
TTFT
20/20
Memory
30/30

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

mistralai/magistral-sma…

Reasoning
14/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
7/15
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