qwen3-next-80b-t48:latest

OLLAMA GGUF

qwen3next · 79.7B · Q4_K_M

Not Rec.

Jul 31, 2026 · Intel Xeon® E5-4620 0

mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Mar 4, 2026 · Apple M4

Global Score

70 vs 69

Hardware Fit

39 vs 50

Quality Score

83 vs 77

Hardware

qwen3-next-80b-t48… mistralai/devstral…

MachineDell Inc. PowerEdge R820MacBook Air

CPUIntel Xeon® E5-4620 0Apple M4

Cores6410

RAM256 GB32 GB

GPUMicrosoft Remote Display Adapter, Microsoft Basic Display AdapterApple M4

OSMicrosoft Windows Server 2022 Datacenter 10.0.20348macOS 26.3

Archx64arm64

Power Modebalancedbalanced

Performance

qwen3-next-80b-t48… mistralai/devstral…

Tokens/sec3.05.7

First chunk3265 ms5007 ms

TTFT3.3 s5.0 s

Load time82.1 sN/A

Memory usage46.9 GB13.2 GB

Memory %18%41%

HW Fit Score Breakdown

qwen3-next-80b-t48:latest

Speed

3/50

TTFT

6/20

Memory

30/30

mistralai/devstral-smal…

Speed

11/50

TTFT

9/20

Memory

30/30

Quality

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

mistralai/devstral-smal…

Reasoning

16/20

Coding

18/20

Instruction

13/20

Structured

14/15

Math

6/15

Multilingual

10/10

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

View qwen3-next-80b-t48… 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