Qwen3-VL-30B-A3B-Instruct qwen3-vl-30b-a3b-instruct
qwen · qwen vision efficient
unranked — no quality signals yet
- params
- 30.5B (A3B)
- arch
- moe
- context
- 256k
- license
- apache-2.0 open weights
- released
- Sep 2025
- downloads/30d
- 435.6k
# architecture
- layers
- 48
- d_model
- 2048
- heads
- 32q / 4kv
- head dim
- 128
- experts
- top-8 of 128
- vocab
- 151936
- family
- qwen3_vl_moe_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: 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_intelligence | 0.70 | — |
| bench_composite | 0.30 | 0.0 |
benchmark panel evidence:
| complete panel | score (0–100) |
|---|---|
| aime-2025-v1 | 0.0 |
missing signals are dropped and the remaining weights renormalized — never imputed.
# trend
methodology changed during this history window; score movement across that boundary is not model movement. See methodology v6.
# benchmarks
| benchmark | score | source | date |
|---|---|---|---|
| Ai2d | 0.8 / 1 | LLM Stats | — |
| AIME 2025 | 0.7 / 1 | LLM Stats | — |
| Arena-hard-v2 | 0.6 / 1 | LLM Stats | — |
| Bfcl-v3 | 0.7 / 1 | LLM Stats | — |
| Blink | 0.7 / 1 | LLM Stats | — |
| Cc-ocr | 0.8 / 1 | LLM Stats | — |
| Charadessta | 0.6 / 1 | LLM Stats | — |
| Charxiv-d | 0.9 / 1 | LLM Stats | — |
| Charxiv-r | 0.5 / 1 | LLM Stats | — |
| Mm-mt-bench | 8.1 | LLM Stats | — |
# where to run
| provider | quant | ctx | $/M in | $/M out | $/M cache | price src | tps | uptime | ✓ |
|---|---|---|---|---|---|---|---|---|---|
| Featherless | — | — | — | — | via hfrouter | — | — | ||
| DeepInfra | fp8 | 256k | $0.15 | $0.60 | — | deepinfra | — | 99.7% | ✓ |
| Novita | bf16 | 128k | $0.20 | $0.70 | — | novita | — | 92.3% | ✓ |
| Phala | 125k | $0.20 | $0.70 | — | phala | — | — | ✓ | |
| Venice | not-available | 125k | $0.25 | $0.90 | — | venice | — | — | ✓ |
| SiliconFlow | fp8 | 256k | $0.29 | $1.00 | — | openrouter | — | 91.8% | ✓ |
sorted by blended price ((3·input + output) / 4 per 1M) · ✓ = the provider's own catalog confirms the offer · "via …" prices are what the aggregator routing the offer charges, not the provider's own list price
# variants
source aliases
- aa
qwen3-vl-30b-a3b-instruct- llmstats
qwen3-vl-30b-a3b-instruct- openrouter
qwen/qwen3-vl-30b-a3b-instruct