Qwen3.6 27B in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
B 1,381 ±11
Percentile 59 · #122 · provisional
People prefer / Solves tasks
— / 1,395
Human votes vs benchmarks, Elo-eq
Value
+2
$1.04 per 1M tokens, median of 22 providers · vendor $1.35
On your hardware
- GPU 12 GB #19 · Q4_K_M · ≈4 tok/s
- GPU 24 GB #6 · Q5_K_S · ≈37 tok/s
- Mac 64 GB #10 · Q8_0 · ≈13 tok/s
- 128 GB unified memory #21 · Q4_K_M · ≈10 tok/s
- CPU, 32 GB RAM #11 · Q4_K_M · ≈2 tok/s
Score decomposition
B General 1,381 [1,370–1,392] Percentile 59 · #122 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
eci
|
146 ±0.87 | 1,410 ±7 | 82.6% | 2026-04-22 | — |
| Epoch AI |
gpqa_diamond
decay ×0.26 |
0.86 ±0.02 | 1,439 ±12 | 2.8% | 2026-08-07 | — |
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
B Math 1,369 [1,359–1,379] Percentile 53 · #121 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
frontiermath_t1_3
decay ×0.86 |
0.35 ±0.03 | 1,397 ±6 | 85.6% | 2026-08-28 | — |
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 |
|---|---|
| Qwen3.6 27B | 1,381 B |
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.