llama-3.1-8b-instruct
LM-STUDIO GGUFllama · 8B · Q8_0
Apr 26, 2026 · AMD Ryzen 5 5500
qwen3.5-35b-a3b-uncensored-hauhaucs-aggressive
LM-STUDIO GGUFqwen35moe · 35B · Q4_K_M
Apr 21, 2026 · Apple M2 Max
Global Score
81 vs 71
Hardware Fit
100 vs 92
Quality Score
73 vs 62
Hardware
llama-3.1-8b-instr… qwen3.5-35b-a3b-un…
MachineASUSMac Studio
CPUAMD Ryzen 5 5500Apple M2 Max
Cores1212
RAM31 GB96 GB
GPUNavi 44 [Radeon RX 9060 XT]Apple M2 Max
OSNobara Linux 43macOS 26.1
Archx64arm64
Power Modeperformancebalanced
Performance
llama-3.1-8b-instr… qwen3.5-35b-a3b-un…
Tokens/sec35.659.8
First chunk52 ms12 ms
TTFT256 ms2.4 s
Load timeN/AN/A
Memory usage8.6 GB29.7 GB
Memory %28%31%
HW Fit Score Breakdown
llama-3.1-8b-instruct
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3.5-35b-a3b-uncenso…
Speed
50/50
TTFT
12/20
Memory
30/30
Quality
llama-3.1-8b-instruct
Reasoning
13/20
Coding
17/20
Instruction
13/20
Structured
15/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
qwen3.5-35b-a3b-uncenso…
Reasoning
18/20
Coding
8/20
Instruction
13/20
Structured
6/15
Math
12/15
Multilingual
5/10
Reasoning: Strong Coding: Weak Instruction Following: Adequate Structured Output: Weak Math: Strong 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