Back to leaderboard

llama3.2:3b

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

Aug 28, 2026 · Intel Core™ i5-10210U

qwen3.8-27b-mlx

LM-STUDIO MLX

qwen3_5 · 27B · 8bit

Marginal

Aug 17, 2026 · Apple M5 Max

Global Score
67 vs 59
Hardware Fit
77 vs 63
Quality Score
63 vs 58

Hardware

llama3.2:3b qwen3.8-27b-mlx
MachineLENOVO 20U30029MBMacBook Pro
CPUIntel Core™ i5-10210UApple M5 Max
Cores818
RAM15 GB64 GB
GPUCometLake-U GT2 [UHD Graphics]Apple M5 Max
OSPop 24.04 LTSmacOS 27.0
Archx64arm64
Power Modelow-powerbalanced

Performance

llama3.2:3b qwen3.8-27b-mlx
Tokens/sec10.018.3
First chunk1166 ms4 ms
TTFT1.2 s530 ms
Load time6.8 sN/A
Memory usage3.8 GB38.5 GB
Memory %25%60%

HW Fit Score Breakdown

llama3.2:3b

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

qwen3.8-27b-mlx

Speed
23/50
TTFT
20/20
Memory
20/30

Quality

llama3.2:3b

Reasoning
11/20
Coding
15/20
Instruction
13/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong

qwen3.8-27b-mlx

Reasoning
19/20
Coding
14/20
Instruction
6/20
Structured
1/15
Math
13/15
Multilingual
5/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak

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