Back to leaderboard

qwen3-coder-30b-a3b-instruct-mlx

LM-STUDIO MLX

qwen3_moe · 30B · 4bit

Excellent

Oct 20, 2026 · Apple M1 Pro

nemotron-3.5-bolt:74b-a9b-iq2

OLLAMA GGUF

nemotron_h_moe · 74.0B · IQ2_XXS

Excellent

Oct 16, 2026 · AMD RYZEN AI MAX+ 395

Global Score
87 vs 90
Hardware Fit
85 vs 96
Quality Score
88 vs 87

Hardware

qwen3-coder-30b-a3… nemotron-3.5-bolt:…
MachineMacBook ProAZW GTR Pro
CPUApple M1 ProAMD RYZEN AI MAX+ 395
Cores1032
RAM32 GB125 GB
GPUApple M1 ProRadeon 8060S
OSmacOS 15.6.1Ubuntu 24.04.5 LTS
Archarm64x64
Power Modebalancedperformance

Performance

qwen3-coder-30b-a3… nemotron-3.5-bolt:…
Tokens/sec45.749.9
First chunk17 ms370 ms
TTFT390 ms370 ms
Load timeN/A7.6 s
Memory usage22.4 GB3.9 GB
Memory %70%3%

HW Fit Score Breakdown

qwen3-coder-30b-a3b-ins…

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

nemotron-3.5-bolt:74b-a…

Speed
46/50
TTFT
20/20
Memory
30/30

Quality

qwen3-coder-30b-a3b-ins…

Reasoning
15/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

nemotron-3.5-bolt:74b-a…

Reasoning
15/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3-coder-30b-a3… details | View nemotron-3.5-bolt:… 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