Back to leaderboard

mlx-community/meta-llama-3.1-8b-instruct

LM-STUDIO MLX

llama · 8B · 4bit

Good

Mar 5, 2026 · Apple M4 Pro

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
77 vs 70
Hardware Fit
100 vs 39
Quality Score
67 vs 83

Hardware

mlx-community/meta… qwen3-next-80b-t48…
MachineMac miniDell Inc. PowerEdge R820
CPUApple M4 ProIntel Xeon® E5-4620 0
Cores1464
RAM64 GB256 GB
GPUApple M4 ProMicrosoft Remote Display Adapter, Microsoft Basic Display Adapter
OSmacOS 15.7.4Microsoft Windows Server 2022 Datacenter 10.0.20348
Archarm64x64
Power Modebalancedbalanced

Performance

mlx-community/meta… qwen3-next-80b-t48…
Tokens/sec54.33.0
First chunk277 ms3265 ms
TTFT277 ms3.3 s
Load timeN/A82.1 s
Memory usage4.2 GB46.9 GB
Memory %7%18%

HW Fit Score Breakdown

mlx-community/meta-llam…

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

qwen3-next-80b-t48:latest

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

Quality

mlx-community/meta-llam…

Reasoning
11/20
Coding
14/20
Instruction
14/20
Structured
15/15
Math
4/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong

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