qwen/qwen3.6-35b-a3b
LM-STUDIO MLXqwen3_5_moe · 35B · 4bit
Jul 17, 2026 · Apple M5 Max
hf.co/LiquidAI/LFM2.5-2.6B-GGUF:F16
OLLAMA GGUFlfm2 · 2.7B · unknown
Aug 23, 2026 · Apple M1 Pro
Global Score
89 vs 61
Hardware Fit
97 vs 97
Quality Score
86 vs 46
Hardware
qwen/qwen3.6-35b-a3b hf.co/LiquidAI/LFM…
MachineMacBook ProMacBook Pro
CPUApple M5 MaxApple M1 Pro
Cores1810
RAM64 GB16 GB
GPUApple M5 MaxApple M1 Pro
OSmacOS 27.0macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen/qwen3.6-35b-a3b hf.co/LiquidAI/LFM…
Tokens/sec130.231.4
First chunk5 ms138 ms
TTFT135 ms138 ms
Load timeN/A3.7 s
Memory usage26.6 GB6.6 GB
Memory %42%41%
HW Fit Score Breakdown
qwen/qwen3.6-35b-a3b
Speed
50/50
TTFT
20/20
Memory
27/30
hf.co/LiquidAI/LFM2.5-2…
Speed
50/50
TTFT
20/20
Memory
27/30
Quality
qwen/qwen3.6-35b-a3b
Reasoning
15/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
hf.co/LiquidAI/LFM2.5-2…
Reasoning
14/20
Coding
13/20
Instruction
3/20
Structured
0/15
Math
14/15
Multilingual
2/10
Reasoning: Adequate Coding: Adequate Instruction Following: Poor Structured Output: Poor Math: Strong Multilingual: Poor
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