Qwen3.5 0.8B qwen3.5-0.8b
qwen · qwen
#102 overall
- params
- 0.9B
- arch
- dense
- license
- apache-2.0 open weights
- released
- Feb 2026
- downloads/30d
- 3.5M
# architecture
- layers
- 24
- d_model
- 1024
- heads
- 8q / 2kv
- head dim
- 256
- vocab
- 248320
- family
- qwen3_5_text
signal path of one layer, generated from the registry's structured fields — dimension lines quote the model's real numbers; an MoE trace forks at the router, a dense trace runs straight through. Geometry fields come from the repo's config.json.
# why ranked
Overall: #102 — score 7.6 ● low — a single signal; treat with caution
| signal | weight | input (0–100) |
|---|---|---|
| aa_intelligence | 0.70 | 6.5 |
| bench_composite | 0.30 | 10.2 |
benchmark panel evidence:
| complete panel | score (0–100) |
|---|---|
| aa-coding-v1 | 10.2 |
Coding: provisional — score — ● low — a single signal; treat with caution
provisional: too few independent signals for a numbered position — the score is shown, but this model sorts after every ranked model.
| signal | weight | input (0–100) |
|---|---|---|
| aa_coding | 0.30 | 0.0 |
| aider_polyglot | 0.30 | — |
| swe_bench_verified | 0.40 | — |
missing signals are dropped and the remaining weights renormalized — never imputed.
# trend
# benchmarks
| benchmark | score | source | date |
|---|---|---|---|
| AA Coding Index | 1.2 | Artificial Analysis | — |
| AA Intelligence Index | 6.1 | Artificial Analysis | — |
| Aa-lcr | 0.0 / 1 | LLM Stats | — |
| Bfcl-v4 | 0.3 / 1 | LLM Stats | — |
| C-eval | 0.5 / 1 | LLM Stats | — |
# where to run
no known API providers — download the weights from Hugging Face and run them yourself.
source aliases
- llmstats
qwen3.5-0.8b