Back to leaderboard

qwen3.8-27b-fable-distill-heretic-ara-i1

LM-STUDIO GGUF

qwen35 · 27B · IQ3_S

Excellent

Aug 19, 2026 · AMD Ryzen 7 9700X 8-Core Processor

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Aug 28, 2026 · Intel Core™ i5-10210U

Global Score
88 vs 64
Hardware Fit
98 vs 69
Quality Score
84 vs 62

Hardware

qwen3.8-27b-fable-… qwen3.5:4b
MachineMicro-Star International Co., Ltd. MS-7E51LENOVO 20U30029MB
CPUAMD Ryzen 7 9700X 8-Core ProcessorIntel Core™ i5-10210U
Cores168
RAM31 GB15 GB
GPUNVIDIA GeForce RTX 5080, AMD Radeon(TM) GraphicsCometLake-U GT2 [UHD Graphics]
OSMicrosoft Windows 11 Pro 10.0.26200Pop 24.04 LTS
Archx64x64
Power Modebalancedperformance

Performance

qwen3.8-27b-fable-… qwen3.5:4b
Tokens/sec48.87.4
First chunk18 ms1815 ms
TTFT276 ms1.8 s
Load timeN/A10.9 s
Memory usage11.7 GB3.5 GB
Memory %38%23%

HW Fit Score Breakdown

qwen3.8-27b-fable-disti…

Speed
50/50
TTFT
20/20
Memory
28/30

qwen3.5:4b

Speed
19/50
TTFT
20/20
Memory
30/30

Quality

qwen3.8-27b-fable-disti…

Reasoning
15/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

qwen3.5:4b

Reasoning
15/20
Coding
14/20
Instruction
6/20
Structured
12/15
Math
6/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3.8-27b-fable-… details | View qwen3.5:4b 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