smollm2-360m-instruct
LM-STUDIO GGUFllama · 360M · Q4_K_M
Mar 5, 2026 · Intel Core™ i5-5300U
qwen3-next:80b-a3b-instruct-q4_K_M
OLLAMA GGUFqwen3next · 79.7B · Q4_K_M
Aug 23, 2026 · Intel Xeon® E5-4650 v2
Global Score
48 vs 74
Hardware Fit
98 vs 42
Quality Score
26 vs 87
Hardware
smollm2-360m-instr… qwen3-next:80b-a3b…
MachineLENOVO 20BUS00700Dell Inc. PowerEdge R820
CPUIntel Core™ i5-5300UIntel Xeon® E5-4650 v2
Cores480
RAM16 GB256 GB
GPUIntel(R) HD Graphics 5500Microsoft Basic Display Adapter
OSMicrosoft Windows 10 Professionnel 10.0.19045Microsoft Windows Server 2022 Datacenter 10.0.20348
Archx64x64
Power Modebalancedbalanced
Performance
smollm2-360m-instr… qwen3-next:80b-a3b…
Tokens/sec20.03.9
First chunk1116 ms2089 ms
TTFT1.1 s2.1 s
Load timeN/A73.3 s
Memory usage0.3 GB46.9 GB
Memory %2%18%
HW Fit Score Breakdown
smollm2-360m-instruct
Speed
50/50
TTFT
20/20
Memory
28/30
qwen3-next:80b-a3b-inst…
Speed
3/50
TTFT
9/20
Memory
30/30
Quality
smollm2-360m-instruct
Reasoning
3/20
Coding
1/20
Instruction
8/20
Structured
8/15
Math
3/15
Multilingual
3/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Adequate Math: Poor Multilingual: Weak
qwen3-next:80b-a3b-inst…
Reasoning
18/20
Coding
19/20
Instruction
12/20
Structured
15/15
Math
13/15
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