Back to leaderboard

deepseek-coder-v2:16b

OLLAMA GGUF

deepseek2 · 15.7B · Q4_0

Excellent

Sep 15, 2026 · Intel Core™ i5-14400F

Qwen3-80B:80B

OLLAMA GGUF

qwen3next · 79.7B · Q4_K_M

Excellent

Aug 22, 2026 · NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )

Global Score
83 vs 87
Hardware Fit
100 vs 76
Quality Score
75 vs 91

Hardware

deepseek-coder-v2:… Qwen3-80B:80B
MachineGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4HP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXML
CPUIntel Core™ i5-14400FNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )
Cores1620
RAM32 GB55 GB
GPUNVIDIA GeForce RTX 5060 TiNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPU
OSMicrosoft Windows 11 Professionnel 10.0.26200Microsoft Windows 11 Pro 10.0.28000
Archx64arm64
Power Modebalancedbalanced

Performance

deepseek-coder-v2:… Qwen3-80B:80B
Tokens/sec150.443.6
First chunk116 ms409 ms
TTFT116 ms409 ms
Load time5.8 s80.3 s
Memory usage9.4 GB48.0 GB
Memory %30%88%

HW Fit Score Breakdown

deepseek-coder-v2:16b

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

Qwen3-80B:80B

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

Quality

deepseek-coder-v2:16b

Reasoning
10/20
Coding
18/20
Instruction
13/20
Structured
12/15
Math
13/15
Multilingual
9/10
Reasoning: Weak Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

Qwen3-80B:80B

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
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest