Back to leaderboard

hf.co/empero-ai/Qwen3.8-2B-Distill-GGUF:BF16

OLLAMA GGUF

qwen35 · 1.94B · BF16

Good

Aug 22, 2026 · Apple M1 Pro

nemotron-3-nano:latest

OLLAMA GGUF

nemotron_h_moe · 31.6B · Q4_K_M

Excellent

Mar 27, 2026 · AMD RYZEN AI MAX+ 395

Global Score
66 vs 89
Hardware Fit
100 vs 100
Quality Score
52 vs 84

Hardware

hf.co/empero-ai/Qw… nemotron-3-nano:la…
MachineMacBook ProAZW GTR Pro
CPUApple M1 ProAMD RYZEN AI MAX+ 395
Cores1032
RAM16 GB125 GB
GPUApple M1 ProRadeon 8060S
OSmacOS 26.6.2Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedperformance

Performance

hf.co/empero-ai/Qw… nemotron-3-nano:la…
Tokens/sec40.265.2
First chunk325 ms295 ms
TTFT325 ms295 ms
Load time3.1 s8.7 s
Memory usage4.7 GB26.0 GB
Memory %30%21%

HW Fit Score Breakdown

hf.co/empero-ai/Qwen3.8…

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

nemotron-3-nano:latest

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

Quality

hf.co/empero-ai/Qwen3.8…

Reasoning
15/20
Coding
9/20
Instruction
8/20
Structured
1/15
Math
15/15
Multilingual
4/10
Reasoning: Adequate Coding: Weak Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak

nemotron-3-nano:latest

Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
View hf.co/empero-ai/Qw… details | View nemotron-3-nano:la… 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