Back to leaderboard

mlx-community/Llama-3.2-3B-Instruct-4bit

LM-STUDIO GGUF
Good

Mar 5, 2026 · Apple M4

qwen3.5:35b-a3b-q4_K_M

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Jul 30, 2026 · Intel Xeon® E5-2637 v3

Global Score
74 vs 49
Hardware Fit
100 vs 54
Quality Score
63 vs 47

Hardware

mlx-community/Llam… qwen3.5:35b-a3b-q4…
MachineMacBook AirDell Inc. Precision Tower 7910
CPUApple M4Intel Xeon® E5-2637 v3
Cores1016
RAM32 GB96 GB
GPUApple M4NVIDIA GeForce RTX 5060 Ti
OSmacOS 26.3Microsoft Windows 10 Pro 10.0.19045
Archarm64x64
Power Modebalancedbalanced

Performance

mlx-community/Llam… qwen3.5:35b-a3b-q4…
Tokens/sec50.621.6
First chunk257 ms1505 ms
TTFT257 ms30.0 s
Load timeN/A53.8 s
Memory usage0.7 GB22.7 GB
Memory %2%24%

HW Fit Score Breakdown

mlx-community/Llama-3.2…

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

qwen3.5:35b-a3b-q4_K_M

Speed
24/50
TTFT
0/20
Memory
30/30

Quality

mlx-community/Llama-3.2…

Reasoning
9/20
Coding
14/20
Instruction
14/20
Structured
15/15
Math
3/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong

qwen3.5:35b-a3b-q4_K_M

Reasoning
14/20
Coding
1/20
Instruction
6/20
Structured
5/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Adequate 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