Back to leaderboard

qwen3.5:0.8b

OLLAMA GGUF

qwen35 · 873.44M · Q8_0

Good

Mar 5, 2026 · Apple M1 Max

llama3.2:3b

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

Jun 25, 2026 · Cortex-A78AE

Global Score
62 vs 74
Hardware Fit
100 vs 99
Quality Score
46 vs 63

Hardware

qwen3.5:0.8b llama3.2:3b
MachineMacBook ProNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUApple M1 MaxCortex-A78AE
Cores106
RAM32 GB7 GB
GPUApple M1 MaxIntegrated / Unknown
OSmacOS 26.3Ubuntu 22.04.5 LTS
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5:0.8b llama3.2:3b
Tokens/sec67.621.1
First chunk209 ms1032 ms
TTFT209 ms1.0 s
Load time1.9 s8.4 s
Memory usage2.6 GB2.4 GB
Memory %8%32%

HW Fit Score Breakdown

qwen3.5:0.8b

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

llama3.2:3b

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

Quality

qwen3.5:0.8b

Reasoning
9/20
Coding
4/20
Instruction
11/20
Structured
13/15
Math
3/15
Multilingual
6/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate

llama3.2:3b

Reasoning
10/20
Coding
14/20
Instruction
15/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor Multilingual: Strong
View qwen3.5:0.8b details | View llama3.2:3b details

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