Back to leaderboard

qwen3-1.7b

LM-STUDIO GGUF

qwen3 · 1.7B · Q4_K_M

Not Rec.

Mar 7, 2026 · Intel Core™ i5-5300U

qwen3.6:35b-mlx

OLLAMA GGUF

nvfp4

Excellent

Jul 17, 2026 · Apple M5 Max

Global Score
19 vs 89
Hardware Fit
64 vs 97
Quality Score
0 vs 86

Hardware

qwen3-1.7b qwen3.6:35b-mlx
MachineLENOVO 20BUS00700MacBook Pro
CPUIntel Core™ i5-5300UApple M5 Max
Cores418
RAM16 GB48 GB
GPUIntel(R) HD Graphics 5500Apple M5 Max
OSMicrosoft Windows 10 Professionnel 10.0.19045macOS 26.5.2
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3-1.7b qwen3.6:35b-mlx
Tokens/sec5.9129.4
First chunk2111 ms49 ms
TTFT2.1 s49 ms
Load timeN/A0.0 s
Memory usage1.2 GB20.5 GB
Memory %8%43%

HW Fit Score Breakdown

qwen3-1.7b

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

qwen3.6:35b-mlx

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

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

qwen3.6:35b-mlx

Reasoning
15/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3-1.7b details | View qwen3.6:35b-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