Back to leaderboard

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

qwen2.5:1.5b

OLLAMA GGUF

qwen2 · 1.5B · Q4_K_M

Good

Jun 17, 2026 · ZHAOXIN KaiXian KX-7000 KaiXian KX-7000

Global Score
78 vs 65
Hardware Fit
74 vs 87
Quality Score
79 vs 56

Hardware

huihui-devstral-sm… qwen2.5:1.5b
MachineSystem manufacturerShanghai Zhaoxin Semiconductor Co., Ltd. ZXE CRB
CPUAMD Ryzen 7 5800X 8-Core ProcessorZHAOXIN KaiXian KX-7000 KaiXian KX-7000
Cores168
RAM32 GB30 GB
GPUAMD Radeon RX 9060 XTZX C-1190
OSMicrosoft Windows 11 Home 10.0.26200Microsoft Windows 11 Pro 10.0.26100
Archx64x64
Power Modebalancedbalanced

Performance

huihui-devstral-sm… qwen2.5:1.5b
Tokens/sec17.516.8
First chunk20 ms941 ms
TTFT279 ms941 ms
Load timeN/A0.2 s
Memory usage15.6 GB1.0 GB
Memory %49%3%

HW Fit Score Breakdown

huihui-devstral-small-2…

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

qwen2.5:1.5b

Speed
37/50
TTFT
20/20
Memory
30/30

Quality

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

qwen2.5:1.5b

Reasoning
8/20
Coding
10/20
Instruction
12/20
Structured
13/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View huihui-devstral-sm… details | View qwen2.5:1.5b details

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