llama3.2:latest
OLLAMA GGUFllama · 3.2B · Q4_K_M
May 27, 2026 · AMD Ryzen 5 2600X Six-Core Processor
huihui-devstral-small-2-24b-instruct-2512-abliterated-i1
LM-STUDIO GGUFmistral3 · 24B · Q4_K_S
Sep 19, 2026 · AMD Ryzen 7 5800X 8-Core Processor
Global Score
76 vs 78
Hardware Fit
100 vs 74
Quality Score
65 vs 79
Hardware
llama3.2:latest huihui-devstral-sm…
MachineMicro-Star International Co., Ltd. MS-7B79System manufacturer
CPUAMD Ryzen 5 2600X Six-Core ProcessorAMD Ryzen 7 5800X 8-Core Processor
Cores1216
RAM16 GB32 GB
GPUNVIDIA GeForce GTX 1080AMD Radeon RX 9060 XT
OSMicrosoft Windows 11 Famille 10.0.26200Microsoft Windows 11 Home 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
llama3.2:latest huihui-devstral-sm…
Tokens/sec57.017.5
First chunk264 ms20 ms
TTFT264 ms279 ms
Load time9.7 sN/A
Memory usage2.6 GB15.6 GB
Memory %16%49%
HW Fit Score Breakdown
llama3.2:latest
Speed
50/50
TTFT
20/20
Memory
30/30
huihui-devstral-small-2…
Speed
29/50
TTFT
20/20
Memory
25/30
Quality
llama3.2:latest
Reasoning
11/20
Coding
15/20
Instruction
15/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor Multilingual: Strong
huihui-devstral-small-2…
Reasoning
16/20
Coding
17/20
Instruction
15/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak 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