Back to leaderboard

hf.co/InternScience/Agents-A1-4B-Q8_0-GGUF:Q8_0

OLLAMA GGUF

qwen35 · 4.21B · unknown

Marginal

Aug 22, 2026 · Apple M1 Pro

llama3.2:3b

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

Jun 25, 2026 · Cortex-A78AE

Global Score
59 vs 74
Hardware Fit
97 vs 99
Quality Score
43 vs 63

Hardware

hf.co/InternScienc… llama3.2:3b
MachineMacBook ProNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUApple M1 ProCortex-A78AE
Cores106
RAM16 GB7 GB
GPUApple M1 ProIntegrated / Unknown
OSmacOS 26.6.2Ubuntu 22.04.5 LTS
Archarm64arm64
Power Modebalancedbalanced

Performance

hf.co/InternScienc… llama3.2:3b
Tokens/sec30.921.1
First chunk891 ms1032 ms
TTFT891 ms1.0 s
Load time3.6 s8.4 s
Memory usage6.6 GB2.4 GB
Memory %41%32%

HW Fit Score Breakdown

hf.co/InternScience/Age…

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

llama3.2:3b

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

Quality

hf.co/InternScience/Age…

Reasoning
13/20
Coding
15/20
Instruction
2/20
Structured
0/15
Math
13/15
Multilingual
0/10
Reasoning: Adequate Coding: Adequate Instruction Following: Poor Structured Output: Poor Math: Strong Multilingual: Poor

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

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