bloomz-560m
LM-STUDIO GGUFbloom · 560M · Q4_K_M
Mar 8, 2026 · Intel Core™ i5-5300U
granite-3.3-2b-instruct
LM-STUDIO MLXgranite · 2B · bf16
Mar 4, 2026 · Apple M4
Global Score
30 vs 66
Hardware Fit
85 vs 87
Quality Score
7 vs 57
Hardware
bloomz-560m granite-3.3-2b-ins…
MachineLENOVO 20BUS00700MacBook Air
CPUIntel Core™ i5-5300UApple M4
Cores410
RAM16 GB32 GB
GPUIntel(R) HD Graphics 5500Apple M4
OSMicrosoft Windows 10 Professionnel 10.0.19045macOS 26.3
Archx64arm64
Power Modebalancedbalanced
Performance
bloomz-560m granite-3.3-2b-ins…
Tokens/sec12.218.3
First chunk1167 ms541 ms
TTFT1.2 s541 ms
Load timeN/AN/A
Memory usage0.5 GB4.7 GB
Memory %3%15%
HW Fit Score Breakdown
bloomz-560m
Speed
38/50
TTFT
20/20
Memory
27/30
granite-3.3-2b-instruct
Speed
37/50
TTFT
20/20
Memory
30/30
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
granite-3.3-2b-instruct
Reasoning
10/20
Coding
10/20
Instruction
14/20
Structured
14/15
Math
2/15
Multilingual
7/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
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