Back to leaderboard

qwen3.8-27b-mlx

LM-STUDIO MLX

qwen3_5 · 27B · 8bit

Marginal

Aug 17, 2026 · Apple M5 Max

qwen3-next-80b-t48:latest

OLLAMA GGUF

qwen3next · 79.7B · Q4_K_M

Not Rec.

Jul 31, 2026 · Intel Xeon® E5-4620 0

Global Score
59 vs 70
Hardware Fit
63 vs 39
Quality Score
58 vs 83

Hardware

qwen3.8-27b-mlx qwen3-next-80b-t48…
MachineMacBook ProDell Inc. PowerEdge R820
CPUApple M5 MaxIntel Xeon® E5-4620 0
Cores1864
RAM64 GB256 GB
GPUApple M5 MaxMicrosoft Remote Display Adapter, Microsoft Basic Display Adapter
OSmacOS 27.0Microsoft Windows Server 2022 Datacenter 10.0.20348
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3.8-27b-mlx qwen3-next-80b-t48…
Tokens/sec18.33.0
First chunk4 ms3265 ms
TTFT530 ms3.3 s
Load timeN/A82.1 s
Memory usage38.5 GB46.9 GB
Memory %60%18%

HW Fit Score Breakdown

qwen3.8-27b-mlx

Speed
23/50
TTFT
20/20
Memory
20/30

qwen3-next-80b-t48:latest

Speed
3/50
TTFT
6/20
Memory
30/30

Quality

qwen3.8-27b-mlx

Reasoning
19/20
Coding
14/20
Instruction
6/20
Structured
1/15
Math
13/15
Multilingual
5/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak

qwen3-next-80b-t48:latest

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