Back to leaderboard

google/gemma-3-27b

LM-STUDIO MLX

gemma3 · 27B · 4bit

Not Rec.

Mar 19, 2026 · Apple M4

Qwen3.8-27B-UD-IQ4_XS_unsloth:latest

OLLAMA GGUF

qwen35 · 27.3B · IQ4_XS

Excellent

Aug 27, 2026 · AMD Ryzen 7 9700X 8-Core Processor

Global Score
71 vs 80
Hardware Fit
35 vs 60
Quality Score
86 vs 89

Hardware

google/gemma-3-27b Qwen3.8-27B-UD-IQ4…
MachineMac miniMicro-Star International Co., Ltd. MS-7E51
CPUApple M4AMD Ryzen 7 9700X 8-Core Processor
Cores1016
RAM24 GB31 GB
GPUApple M4NVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

google/gemma-3-27b Qwen3.8-27B-UD-IQ4…
Tokens/sec5.910.8
First chunk19 ms891 ms
TTFT1.8 s891 ms
Load timeN/A0.0 s
Memory usage22.0 GB17.6 GB
Memory %92%57%

HW Fit Score Breakdown

google/gemma-3-27b

Speed
12/50
TTFT
19/20
Memory
4/30

Qwen3.8-27B-UD-IQ4_XS_u…

Speed
18/50
TTFT
20/20
Memory
22/30

Quality

google/gemma-3-27b

Reasoning
16/20
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

Qwen3.8-27B-UD-IQ4_XS_u…

Reasoning
17/20
Coding
18/20
Instruction
18/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View google/gemma-3-27b details | View Qwen3.8-27B-UD-IQ4… 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