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

qwen2.5-coder:7b

OLLAMA GGUF

qwen2 · 7.6B · Q4_K_M

Good

Mar 5, 2026 · Intel Gen Intel® Core™ i7-13700K

Global Score
88 vs 68
Hardware Fit
70 vs 59
Quality Score
96 vs 72

Hardware

qwen3.8-27b-fable-… qwen2.5-coder:7b
MachineMacBook ProASUS
CPUApple M4 MaxIntel Gen Intel® Core™ i7-13700K
Cores1624
RAM128 GB64 GB
GPUApple M4 MaxNVIDIA GeForce RTX 3070
OSmacOS 26.5.2Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedunknown

Performance

qwen3.8-27b-fable-… qwen2.5-coder:7b
Tokens/sec30.434.4
First chunk27 ms1991 ms
TTFT4.4 s2.0 s
Load timeN/A40.6 s
Memory usage19.9 GB5.0 GB
Memory %16%8%

HW Fit Score Breakdown

qwen3.8-27b-fable-fusio…

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

qwen2.5-coder:7b

Speed
38/50
TTFT
12/20
Memory
9/30

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

qwen2.5-coder:7b

Reasoning
11/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
9/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

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