qwen/qwen3.5-35b-a3b
LM-STUDIO GGUFqwen35moe · 35B · Q6_K
Sep 19, 2026 · AMD Ryzen 7 5800X 8-Core Processor
hf.co/unsloth/gemma-4-E4B-it-GGUF:Q5_K_M
OLLAMA GGUFgemma4 · 7.52B · unknown
Aug 23, 2026 · Apple M1 Pro
Global Score
72 vs 88
Hardware Fit
35 vs 100
Quality Score
88 vs 83
Hardware
qwen/qwen3.5-35b-a3b hf.co/unsloth/gemm…
MachineSystem manufacturerMacBook Pro
CPUAMD Ryzen 7 5800X 8-Core ProcessorApple M1 Pro
Cores1610
RAM32 GB16 GB
GPUAMD Radeon RX 9060 XTApple M1 Pro
OSMicrosoft Windows 11 Home 10.0.26200macOS 26.6.2
Archx64arm64
Power Modebalancedbalanced
Performance
qwen/qwen3.5-35b-a3b hf.co/unsloth/gemm…
Tokens/sec8.328.3
First chunk32 ms224 ms
TTFT2.0 s224 ms
Load timeN/A4.5 s
Memory usage28.9 GB3.6 GB
Memory %91%23%
HW Fit Score Breakdown
qwen/qwen3.5-35b-a3b
Speed
13/50
TTFT
17/20
Memory
5/30
hf.co/unsloth/gemma-4-E…
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
qwen/qwen3.5-35b-a3b
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
hf.co/unsloth/gemma-4-E…
Reasoning
14/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong 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