qwen3-next:80b-a3b-instruct-q4_K_M
OLLAMA GGUFqwen3next · 79.7B · Q4_K_M
Aug 18, 2026 · Intel Xeon® E5-2637 v3
ministral-3:8b
OLLAMA GGUFmistral3 · 8.9B · Q4_K_M
Aug 25, 2026 · Apple M1 Pro
Global Score
78 vs 72
Hardware Fit
51 vs 71
Quality Score
89 vs 72
Hardware
qwen3-next:80b-a3b… ministral-3:8b
MachineDell Inc. Precision Tower 7910MacBook Pro
CPUIntel Xeon® E5-2637 v3Apple M1 Pro
Cores1610
RAM96 GB16 GB
GPUNVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060Apple M1 Pro
OSMicrosoft Windows 10 Pro 10.0.19045macOS 26.6.2
Archx64arm64
Power Modebalancedbalanced
Performance
qwen3-next:80b-a3b… ministral-3:8b
Tokens/sec8.719.8
First chunk1251 ms269 ms
TTFT1.3 s269 ms
Load time61.6 s10.7 s
Memory usage48.3 GB13.7 GB
Memory %50%86%
HW Fit Score Breakdown
qwen3-next:80b-a3b-inst…
Speed
9/50
TTFT
17/20
Memory
25/30
ministral-3:8b
Speed
44/50
TTFT
20/20
Memory
7/30
Quality
qwen3-next:80b-a3b-inst…
Reasoning
18/20
Coding
19/20
Instruction
14/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
ministral-3:8b
Reasoning
12/20
Coding
18/20
Instruction
13/20
Structured
13/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest