qwen3-next:80b-a3b-instruct-q4_K_M

OLLAMA GGUF

qwen3next · 79.7B · Q4_K_M

Excellent

Aug 1, 2026 · Intel Xeon® E5-2637 v3

mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Oct 20, 2026 · Apple M1 Pro

Global Score

80 vs 73

Hardware Fit

54 vs 64

Quality Score

91 vs 77

Hardware

qwen3-next:80b-a3b… mistralai/devstral…

MachineDell Inc. Precision Tower 7910MacBook Pro

CPUIntel Xeon® E5-2637 v3Apple M1 Pro

Cores1610

RAM96 GB32 GB

GPUNVIDIA GeForce RTX 5060 TiApple M1 Pro

OSMicrosoft Windows 10 Pro 10.0.19045macOS 15.6.1

Archx64arm64

Power Modebalancedbalanced

Performance

qwen3-next:80b-a3b… mistralai/devstral…

Tokens/sec14.911.9

First chunk1808 ms7 ms

TTFT1.8 s1.1 s

Load time95.0 sN/A

Memory usage48.0 GB19.7 GB

Memory %50%62%

HW Fit Score Breakdown

qwen3-next:80b-a3b-inst…

Speed

16/50

TTFT

13/20

Memory

25/30

mistralai/devstral-smal…

Speed

25/50

TTFT

20/20

Memory

19/30

Quality

qwen3-next:80b-a3b-inst…

Reasoning

18/20

Coding

19/20

Instruction

16/20

Structured

15/15

Math

13/15

Multilingual

10/10

Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

mistralai/devstral-smal…

Reasoning

17/20

Coding

16/20

Instruction

13/20

Structured

14/15

Math

7/15

Multilingual

10/10

Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

View qwen3-next:80b-a3b… details | View mistralai/devstral… 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