qwen3-coder-next:latest
OLLAMA GGUFqwen3next · 79.7B · Q4_K_M
Mar 5, 2026 · AMD RYZEN AI MAX+ 395
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
82 vs 78
Hardware Fit
71 vs 74
Quality Score
87 vs 79
Hardware
qwen3-coder-next:l… huihui-devstral-sm…
MachineAZW GTR ProSystem manufacturer
CPUAMD RYZEN AI MAX+ 395AMD Ryzen 7 5800X 8-Core Processor
Cores3216
RAM125 GB32 GB
GPUAMD Radeon 8060SAMD Radeon RX 9060 XT
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Home 10.0.26200
Archx64x64
Power Modeperformancebalanced
Performance
qwen3-coder-next:l… huihui-devstral-sm…
Tokens/sec34.517.5
First chunk262 ms20 ms
TTFT262 ms279 ms
Load time16.4 sN/A
Memory usage56.8 GB15.6 GB
Memory %46%49%
HW Fit Score Breakdown
qwen3-coder-next:latest
Speed
34/50
TTFT
20/20
Memory
17/30
huihui-devstral-small-2…
Speed
29/50
TTFT
20/20
Memory
25/30
Quality
qwen3-coder-next:latest
Reasoning
18/20
Coding
18/20
Instruction
13/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong 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