Back to leaderboard

qwen/qwen3.5-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q6_K

Not Rec.

Sep 19, 2026 · AMD Ryzen 7 5800X 8-Core Processor

huihui-devstral-small-2-24b-instruct-2512-abliterated-i1

LM-STUDIO GGUF

mistral3 · 24B · Q4_K_S

Good

Sep 19, 2026 · AMD Ryzen 7 5800X 8-Core Processor

Global Score
72 vs 78
Hardware Fit
35 vs 74
Quality Score
88 vs 79

Hardware

qwen/qwen3.5-35b-a3b huihui-devstral-sm…
MachineSystem manufacturerSystem manufacturer
CPUAMD Ryzen 7 5800X 8-Core ProcessorAMD Ryzen 7 5800X 8-Core Processor
Cores1616
RAM32 GB32 GB
GPUAMD Radeon RX 9060 XTAMD Radeon RX 9060 XT
OSMicrosoft Windows 11 Home 10.0.26200Microsoft Windows 11 Home 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

qwen/qwen3.5-35b-a3b huihui-devstral-sm…
Tokens/sec8.317.5
First chunk32 ms20 ms
TTFT2.0 s279 ms
Load timeN/AN/A
Memory usage28.9 GB15.6 GB
Memory %91%49%

HW Fit Score Breakdown

qwen/qwen3.5-35b-a3b

Speed
13/50
TTFT
17/20
Memory
5/30

huihui-devstral-small-2…

Speed
29/50
TTFT
20/20
Memory
25/30

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

huihui-devstral-small-2…

Reasoning
16/20
Coding
17/20
Instruction
15/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest