deepseek-r1:latest
OLLAMA GGUFqwen2 · 7.6B · Q4_K_M
Jun 25, 2026 · Cortex-A78AE
qwen3-next:80b-a3b-instruct-q4_K_M
OLLAMA GGUFqwen3next · 79.7B · Q4_K_M
Aug 1, 2026 · Intel Xeon® E5-2637 v3
Global Score
23 vs 80
Hardware Fit
70 vs 54
Quality Score
3 vs 91
Hardware
deepseek-r1:latest qwen3-next:80b-a3b…
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperDell Inc. Precision Tower 7910
CPUCortex-A78AEIntel Xeon® E5-2637 v3
Cores616
RAM7 GB96 GB
GPUIntegrated / UnknownNVIDIA GeForce RTX 5060 Ti
OSUbuntu 22.04.5 LTSMicrosoft Windows 10 Pro 10.0.19045
Archarm64x64
Power Modebalancedbalanced
Performance
deepseek-r1:latest qwen3-next:80b-a3b…
Tokens/sec9.814.9
First chunk1206 ms1808 ms
TTFT1.2 s1.8 s
Load time17.8 s95.0 s
Memory usage4.8 GB48.0 GB
Memory %65%50%
HW Fit Score Breakdown
deepseek-r1:latest
Speed
32/50
TTFT
20/20
Memory
18/30
qwen3-next:80b-a3b-inst…
Speed
16/50
TTFT
13/20
Memory
25/30
Quality
deepseek-r1:latest
Reasoning
0/20
Coding
1/20
Instruction
0/20
Structured
0/15
Math
2/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
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
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