Back to leaderboard

deepseek-coder-1.3b-instruct

LM-STUDIO GGUF

llama · 1.3B · Q8_0

Not Rec.

Mar 6, 2026 · Intel Core™ i5-5300U

qwen/qwen3.8-27b

LM-STUDIO MLX

qwen3_5 · 27B · 8bit

Excellent

Aug 18, 2026 · Apple M4 Max

Global Score
30 vs 81
Hardware Fit
66 vs 68
Quality Score
14 vs 87

Hardware

deepseek-coder-1.3… qwen/qwen3.8-27b
MachineLENOVO 20BUS00700MacBook Pro
CPUIntel Core™ i5-5300UApple M4 Max
Cores416
RAM16 GB128 GB
GPUIntel(R) HD Graphics 5500Apple M4 Max
OSMicrosoft Windows 10 Professionnel 10.0.19045macOS 26.5.2
Archx64arm64
Power Modebalancedbalanced

Performance

deepseek-coder-1.3… qwen/qwen3.8-27b
Tokens/sec7.116.4
First chunk3448 ms5 ms
TTFT3.4 s742 ms
Load timeN/AN/A
Memory usage1.3 GB38.5 GB
Memory %9%30%

HW Fit Score Breakdown

deepseek-coder-1.3b-ins…

Speed
24/50
TTFT
15/20
Memory
27/30

qwen/qwen3.8-27b

Speed
18/50
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

qwen/qwen3.8-27b

Reasoning
17/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

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