gemma-3-1b-it
LM-STUDIO GGUFgemma3 · 1B · Q4_K_M
Mar 5, 2026 · Intel Core™ i5-5300U
qwen3.8-27b-mlx
LM-STUDIO UNKNOWN27B
Aug 17, 2026 · Apple M5 Max
Global Score
59 vs 66
Hardware Fit
76 vs 91
Quality Score
52 vs 55
Hardware
gemma-3-1b-it qwen3.8-27b-mlx
MachineLENOVO 20BUS00700MacBook Pro
CPUIntel Core™ i5-5300UApple M5 Max
Cores418
RAM16 GB64 GB
GPUIntel(R) HD Graphics 5500Apple M5 Max
OSMicrosoft Windows 10 Professionnel 10.0.19045macOS 27.0
Archx64arm64
Power Modebalancedbalanced
Performance
gemma-3-1b-it qwen3.8-27b-mlx
Tokens/sec8.733.2
First chunk2078 ms7 ms
TTFT2.1 s311 ms
Load timeN/AN/A
Memory usage0.8 GB0.5 GB
Memory %5%1%
HW Fit Score Breakdown
gemma-3-1b-it
Speed
29/50
TTFT
19/20
Memory
28/30
qwen3.8-27b-mlx
Speed
41/50
TTFT
20/20
Memory
30/30
Quality
gemma-3-1b-it
Reasoning
4/20
Coding
11/20
Instruction
14/20
Structured
13/15
Math
2/15
Multilingual
8/10
Reasoning: Poor Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
qwen3.8-27b-mlx
Reasoning
19/20
Coding
13/20
Instruction
6/20
Structured
0/15
Math
14/15
Multilingual
3/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest