deepseek-coder-1.3b-instruct

LM-STUDIO GGUF

llama · 1.3B · Q8_0

Not Rec.

Mar 6, 2026 · Intel Core™ i5-5300U

llama3.2:3b

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

Aug 28, 2026 · Intel Core™ i5-10210U

Global Score

30 vs 67

Hardware Fit

66 vs 77

Quality Score

14 vs 63

Hardware

deepseek-coder-1.3… llama3.2:3b

MachineLENOVO 20BUS00700LENOVO 20U30029MB

CPUIntel Core™ i5-5300UIntel Core™ i5-10210U

Cores48

RAM16 GB15 GB

GPUIntel(R) HD Graphics 5500CometLake-U GT2 [UHD Graphics]

OSMicrosoft Windows 10 Professionnel 10.0.19045Pop 24.04 LTS

Archx64x64

Power Modebalancedlow-power

Performance

deepseek-coder-1.3… llama3.2:3b

Tokens/sec7.110.0

First chunk3448 ms1166 ms

TTFT3.4 s1.2 s

Load timeN/A6.8 s

Memory usage1.3 GB3.8 GB

Memory %9%25%

HW Fit Score Breakdown

deepseek-coder-1.3b-ins…

Speed

24/50

TTFT

15/20

Memory

27/30

llama3.2:3b

Speed

27/50

TTFT

20/20

Memory

30/30

Quality

deepseek-coder-1.3b-ins…

Reasoning

0/20

Coding

3/20

Instruction

3/20

Structured

6/15

Math

0/15

Multilingual

2/10

Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Weak Math: Poor Multilingual: Poor

llama3.2:3b

Reasoning

11/20

Coding

15/20

Instruction

13/20

Structured

12/15

Math

3/15

Multilingual

9/10

Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong

View deepseek-coder-1.3… details | View llama3.2:3b 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