Back to leaderboard

deepseek-r1-distill-qwen-14b-mlx

LM-STUDIO MLX

qwen2 · 14B · 5bit

Not Rec.

Mar 11, 2026 · Apple M4

nvidia-nemotron-3-nano-4b

LM-STUDIO GGUF

nemotron_h · 4B · Q4_K_M

Excellent

Oct 24, 2026 · Intel Core™ i3-9100F

Global Score
36 vs 83
Hardware Fit
53 vs 100
Quality Score
28 vs 75

Hardware

deepseek-r1-distil… nvidia-nemotron-3-…
MachineMac miniGigabyte Technology Co., Ltd. H310M S2 2.0
CPUApple M4Intel Core™ i3-9100F
Cores104
RAM24 GB16 GB
GPUApple M4Virtual Desktop Monitor, NVIDIA GeForce GTX 1650
OSmacOS 26.3Майкрософт Windows 10 Pro 10.0.19045
Archarm64x64
Power Modebalancedbalanced

Performance

deepseek-r1-distil… nvidia-nemotron-3-…
Tokens/sec10.328.9
First chunk27 ms22 ms
TTFT20.7 s580 ms
Load time15.4 sN/A
Memory usage1.0 GB3.8 GB
Memory %4%24%

HW Fit Score Breakdown

deepseek-r1-distill-qwe…

Speed
23/50
TTFT
0/20
Memory
30/30

nvidia-nemotron-3-nano-4b

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

Quality

deepseek-r1-distill-qwe…

Reasoning
3/20
Coding
6/20
Instruction
6/20
Structured
3/15
Math
2/15
Multilingual
8/10
Reasoning: Poor Coding: Weak Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Strong

nvidia-nemotron-3-nano-4b

Reasoning
15/20
Coding
12/20
Instruction
16/20
Structured
14/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View deepseek-r1-distil… details | View nvidia-nemotron-3-… 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