bloomz-560m
LM-STUDIO GGUFbloom · 560M · Q4_K_M
Mar 8, 2026 · Intel Core™ i5-5300U
GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 22, 2026 · NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )
Global Score
30 vs 66
Hardware Fit
85 vs 23
Quality Score
7 vs 84
Hardware
bloomz-560m GPT-120B:120b
MachineLENOVO 20BUS00700HP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXML
CPUIntel Core™ i5-5300UNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )
Cores420
RAM16 GB55 GB
GPUIntel(R) HD Graphics 5500NVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPU
OSMicrosoft Windows 10 Professionnel 10.0.19045Microsoft Windows 11 Pro 10.0.28000
Archx64arm64
Power Modebalancedbalanced
Performance
bloomz-560m GPT-120B:120b
Tokens/sec12.216.8
First chunk1167 ms11247 ms
TTFT1.2 s12.2 s
Load timeN/A77.3 s
Memory usage0.5 GB61.6 GB
Memory %3%113%
HW Fit Score Breakdown
bloomz-560m
Speed
38/50
TTFT
20/20
Memory
27/30
GPT-120B:120b
Speed
21/50
TTFT
2/20
Memory
0/30
Quality
bloomz-560m
Reasoning
4/20
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
GPT-120B:120b
Reasoning
16/20
Coding
19/20
Instruction
11/20
Structured
13/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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