Back to leaderboard

qwen3.8-27b-fable-fusion-f711-gain-mlx

LM-STUDIO MLX

qwen3_5 · 27B · MXFP4

Excellent

Aug 20, 2026 · Apple M4 Max

gemma4:26b

OLLAMA GGUF

gemma4 · 25.8B · Q4_K_M

Not Rec.

Jul 7, 2026 · Cortex-X925

Global Score
88 vs 88
Hardware Fit
70 vs 80
Quality Score
96 vs 92

Hardware

qwen3.8-27b-fable-… gemma4:26b
MachineMacBook ProASUSTeK COMPUTER INC. GX10
CPUApple M4 MaxCortex-X925
Cores1620
RAM128 GB122 GB
GPUApple M4 MaxDevice 2e12
OSmacOS 26.5.2Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance

Performance

qwen3.8-27b-fable-… gemma4:26b
Tokens/sec30.466.7
First chunk27 ms583 ms
TTFT4.4 s30.0 s
Load timeN/A6.7 s
Memory usage19.9 GB17.6 GB
Memory %16%15%

HW Fit Score Breakdown

qwen3.8-27b-fable-fusio…

Speed
34/50
TTFT
6/20
Memory
30/30

gemma4:26b

Speed
50/50
TTFT
0/20
Memory
30/30

Quality

qwen3.8-27b-fable-fusio…

Reasoning
19/20
Coding
19/20
Instruction
18/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

gemma4:26b

Reasoning
19/20
Coding
17/20
Instruction
17/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.8-27b-fable-… details | View gemma4:26b 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