Back to leaderboard

deepseek-r1:1.5b

OLLAMA GGUF

qwen2 · 1.8B · Q4_K_M

Not Rec.

Apr 29, 2026 · Intel Core™ i5-8350U

tinyllama

OLLAMA GGUF
Marginal

Mar 6, 2026 · Apple M4

Global Score
37 vs 43
Hardware Fit
73 vs 100
Quality Score
22 vs 19

Hardware

deepseek-r1:1.5b tinyllama
MachineLENOVO 20L7CTO1WWMacBook Air
CPUIntel Core™ i5-8350UApple M4
Cores810
RAM23 GB32 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]Apple M4
OSFedora Linux 43macOS 26.3
Archx64arm64
Power Modelow-powerbalanced

Performance

deepseek-r1:1.5b tinyllama
Tokens/sec18.4133.4
First chunk593 ms61 ms
TTFT30.0 s61 ms
Load time3.8 s0.5 s
Memory usage1.0 GB0.2 GB
Memory %4%1%

HW Fit Score Breakdown

deepseek-r1:1.5b

Speed
43/50
TTFT
0/20
Memory
30/30

tinyllama

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

Quality

deepseek-r1:1.5b

Reasoning
4/20
Coding
0/20
Instruction
5/20
Structured
3/15
Math
7/15
Multilingual
3/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Weak Multilingual: Weak

tinyllama

Reasoning
2/20
Coding
2/20
Instruction
7/20
Structured
5/15
Math
0/15
Multilingual
3/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Poor Multilingual: Weak
View deepseek-r1:1.5b details | View tinyllama 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