Qwen3.5-9B in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
C 1,330 ±16
Percentile 42 · #170 · provisional
People prefer / Solves tasks
— / 1,342
Human votes vs benchmarks, Elo-eq
Value
+4
$0.1188 per 1M tokens, median of 20 providers
On your hardware
- GPU 12 GB #9 · Q6_K · ≈36 tok/s
- GPU 24 GB #14 · Q8_0 · ≈74 tok/s
- Mac 64 GB #13 · Q8_0 · ≈38 tok/s
- 128 GB unified memory #23 · Q8_0 · ≈18 tok/s
- CPU, 32 GB RAM #12 · Q4_K_M · ≈5 tok/s
Score decomposition
C General 1,330 [1,314–1,347] Percentile 42 · #170 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
eci
|
139 ±1.34 | 1,355 ±11 | 79.3% | 2026-02-24 | — |
| Epoch AI |
gpqa_diamond
decay ×0.26 |
0.79 ±0.02 | 1,407 ±11 | 3.4% | 2026-08-27 | — |
Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology
History
The same in a table
| Model | 2026-10 |
|---|---|
| Qwen3.5-9B | 1,330 C |
Badge
Show the model's fedi-index on your site or in a README. The badge updates itself; it links to this page.
Data CC BY 4.0: keep the link to fedi.software.