Back to leaderboard

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

OLLAMA GGUF

qwen35 · 1.94B · BF16

Good

Aug 26, 2026 · Apple M1 Pro

deepseek-coder-v2:16b

OLLAMA GGUF

deepseek2 · 15.7B · Q4_0

Excellent

Sep 15, 2026 · Intel Core™ i5-14400F

Global Score
66 vs 83
Hardware Fit
100 vs 100
Quality Score
52 vs 75

Hardware

hf.co/empero-ai/Qw… deepseek-coder-v2:…
MachineMacBook ProGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4
CPUApple M1 ProIntel Core™ i5-14400F
Cores1016
RAM16 GB32 GB
GPUApple M1 ProNVIDIA GeForce RTX 5060 Ti
OSmacOS 26.6.2Microsoft Windows 11 Professionnel 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

hf.co/empero-ai/Qw… deepseek-coder-v2:…
Tokens/sec40.2150.4
First chunk101 ms116 ms
TTFT101 ms116 ms
Load time2.6 s5.8 s
Memory usage4.7 GB9.4 GB
Memory %30%30%

HW Fit Score Breakdown

hf.co/empero-ai/Qwen3.8…

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

deepseek-coder-v2:16b

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

deepseek-coder-v2:16b

Reasoning
10/20
Coding
18/20
Instruction
13/20
Structured
12/15
Math
13/15
Multilingual
9/10
Reasoning: Weak Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
View hf.co/empero-ai/Qw… details | View deepseek-coder-v2:… 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