qwen/qwen3.6-35b-a3b
LM-STUDIO GGUFqwen35moe · 35B · Q4_K_M
Sep 20, 2026 · AMD Ryzen 7 5800X 8-Core Processor
mistralai/devstral-small-2-2512
LM-STUDIO MLXmistral3 · 24B · 4bit
Oct 20, 2026 · Apple M1 Pro
Global Score
80 vs 73
Hardware Fit
60 vs 64
Quality Score
88 vs 77
Hardware
qwen/qwen3.6-35b-a3b mistralai/devstral…
MachineSystem manufacturerMacBook Pro
CPUAMD Ryzen 7 5800X 8-Core ProcessorApple M1 Pro
Cores1610
RAM31 GB32 GB
GPUNavi 44 [Radeon RX 9060 XT]Apple M1 Pro
OSUbuntu 26.04.1 LTSmacOS 15.6.1
Archx64arm64
Power Modeperformancebalanced
Performance
qwen/qwen3.6-35b-a3b mistralai/devstral…
Tokens/sec15.011.9
First chunk49 ms7 ms
TTFT759 ms1.1 s
Load timeN/AN/A
Memory usage22.2 GB19.7 GB
Memory %71%62%
HW Fit Score Breakdown
qwen/qwen3.6-35b-a3b
Speed
25/50
TTFT
20/20
Memory
15/30
mistralai/devstral-smal…
Speed
25/50
TTFT
20/20
Memory
19/30
Quality
qwen/qwen3.6-35b-a3b
Reasoning
16/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
mistralai/devstral-smal…
Reasoning
17/20
Coding
16/20
Instruction
13/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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