qwen3.5-35b-a3b-uncensored-hauhaucs-aggressive
OPENAI GGUFApr 21, 2026 · Apple M2 Max
deepseek-r1:70b
OLLAMA GGUFllama · 70.6B · Q4_K_M
Jun 27, 2026 · Cortex-X925
Global Score
62 vs 47
Hardware Fit
100 vs 51
Quality Score
45 vs 45
Hardware
qwen3.5-35b-a3b-un… deepseek-r1:70b
MachineMac StudioNVIDIA NVIDIA_DGX_Spark
CPUApple M2 MaxCortex-X925
Cores1220
RAM96 GB122 GB
GPUApple M2 MaxDevice 2e12
OSmacOS 26.1Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance
Performance
qwen3.5-35b-a3b-un… deepseek-r1:70b
Tokens/sec67.94.7
First chunk50 ms557 ms
TTFT75 ms557 ms
Load time0.0 s52.6 s
Memory usage0.0 GB49.5 GB
Memory %0%41%
HW Fit Score Breakdown
qwen3.5-35b-a3b-uncenso…
Speed
50/50
TTFT
20/20
Memory
30/30
deepseek-r1:70b
Speed
4/50
TTFT
20/20
Memory
27/30
Quality
qwen3.5-35b-a3b-uncenso…
Reasoning
16/20
Coding
0/20
Instruction
12/20
Structured
0/15
Math
8/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Poor Math: Adequate Multilingual: Strong
deepseek-r1:70b
Reasoning
3/20
Coding
1/20
Instruction
14/20
Structured
9/15
Math
8/15
Multilingual
10/10
Reasoning: Poor Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Adequate 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