Back to leaderboard

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

OLLAMA GGUF

qwen35 · 1.94B · BF16

Good

Aug 23, 2026 · Apple M1 Pro

nemotron-3.5-lightning:latest

OLLAMA GGUF

nemotron_h_moe · 32.9B · Q4_K_M

Not Rec.

Aug 17, 2026 · Cortex-X925

Global Score
66 vs 87
Hardware Fit
100 vs 80
Quality Score
52 vs 90

Hardware

hf.co/empero-ai/Qw… nemotron-3.5-light…
MachineMacBook ProASUSTeK COMPUTER INC. GX10
CPUApple M1 ProCortex-X925
Cores1020
RAM16 GB122 GB
GPUApple M1 ProDevice 2e12
OSmacOS 26.6.2Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance

Performance

hf.co/empero-ai/Qw… nemotron-3.5-light…
Tokens/sec40.484.1
First chunk93 ms371 ms
TTFT93 ms30.0 s
Load time2.7 s0.3 s
Memory usage4.7 GB24.9 GB
Memory %30%20%

HW Fit Score Breakdown

hf.co/empero-ai/Qwen3.8…

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

nemotron-3.5-lightning:…

Speed
50/50
TTFT
0/20
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-3.5-lightning:…

Reasoning
19/20
Coding
17/20
Instruction
17/20
Structured
13/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View hf.co/empero-ai/Qw… details | View nemotron-3.5-light… 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