Back to leaderboard

gemma-3-27b-it-qat

LM-STUDIO MLX

gemma3 · 27B · 4bit

Good

Mar 5, 2026 · Apple M4 Pro

qwen/qwen3.5-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q6_K

Not Rec.

Sep 19, 2026 · AMD Ryzen 7 5800X 8-Core Processor

Global Score
76 vs 72
Hardware Fit
51 vs 35
Quality Score
87 vs 88

Hardware

gemma-3-27b-it-qat qwen/qwen3.5-35b-a3b
MachineMac miniSystem manufacturer
CPUApple M4 ProAMD Ryzen 7 5800X 8-Core Processor
Cores1416
RAM64 GB32 GB
GPUApple M4 ProAMD Radeon RX 9060 XT
OSmacOS 15.7.4Microsoft Windows 11 Home 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

gemma-3-27b-it-qat qwen/qwen3.5-35b-a3b
Tokens/sec8.98.3
First chunk3976 ms32 ms
TTFT4.0 s2.0 s
Load timeN/AN/A
Memory usage15.7 GB28.9 GB
Memory %25%91%

HW Fit Score Breakdown

gemma-3-27b-it-qat

Speed
12/50
TTFT
9/20
Memory
30/30

qwen/qwen3.5-35b-a3b

Speed
13/50
TTFT
17/20
Memory
5/30

Quality

gemma-3-27b-it-qat

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

qwen/qwen3.5-35b-a3b

Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View gemma-3-27b-it-qat details | View qwen/qwen3.5-35b-a3b 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