Back to leaderboard

qwen3-1.7b

LM-STUDIO GGUF

qwen3 · 1.7B · Q4_K_M

Not Rec.

Mar 7, 2026 · Intel Core™ i5-5300U

gemma4:e4b-mlx

OLLAMA GGUF
Not Rec.

Jul 7, 2026 · Apple M2 Pro

Global Score
19 vs 78
Hardware Fit
64 vs 72
Quality Score
0 vs 81

Hardware

qwen3-1.7b gemma4:e4b-mlx
MachineLENOVO 20BUS00700MacBook Pro
CPUIntel Core™ i5-5300UApple M2 Pro
Cores410
RAM16 GB16 GB
GPUIntel(R) HD Graphics 5500Apple M2 Pro
OSMicrosoft Windows 10 Professionnel 10.0.19045macOS 26.5
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3-1.7b gemma4:e4b-mlx
Tokens/sec5.926.9
First chunk2111 ms222 ms
TTFT2.1 s222 ms
Load timeN/A0.1 s
Memory usage1.2 GB15.4 GB
Memory %8%96%

HW Fit Score Breakdown

qwen3-1.7b

Speed
21/50
TTFT
19/20
Memory
24/30

gemma4:e4b-mlx

Speed
50/50
TTFT
20/20
Memory
2/30

Quality

qwen3-1.7b

Reasoning
0/20
Coding
0/20
Instruction
0/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

gemma4:e4b-mlx

Reasoning
14/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3-1.7b details | View gemma4:e4b-mlx 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