Back to leaderboard

qwen3.5:0.8b

OLLAMA GGUF

qwen35 · 873.44M · Q8_0

Not Rec.

Apr 29, 2026 · Intel Core™ i5-8350U

Gemma4-26B:26b

OLLAMA GGUF

gemma4 · 25.8B · 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
18 vs 92
Hardware Fit
53 vs 100
Quality Score
3 vs 89

Hardware

qwen3.5:0.8b Gemma4-26B:26b
MachineLENOVO 20L7CTO1WWHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXML
CPUIntel Core™ i5-8350UNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )
Cores820
RAM23 GB55 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]NVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPU
OSFedora Linux 43Microsoft Windows 11 Pro 10.0.28000
Archx64arm64
Power Modelow-powerbalanced

Performance

qwen3.5:0.8b Gemma4-26B:26b
Tokens/sec9.461.3
First chunk799 ms185 ms
TTFT30.0 s185 ms
Load time3.3 s22.9 s
Memory usage1.9 GB16.4 GB
Memory %8%30%

HW Fit Score Breakdown

qwen3.5:0.8b

Speed
23/50
TTFT
0/20
Memory
30/30

Gemma4-26B:26b

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

Quality

qwen3.5:0.8b

Reasoning
0/20
Coding
0/20
Instruction
2/20
Structured
0/15
Math
0/15
Multilingual
1/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

Gemma4-26B:26b

Reasoning
16/20
Coding
19/20
Instruction
17/20
Structured
14/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.5:0.8b details | View Gemma4-26B:26b 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