Model Catalog › ollama

qwen3.8-flash-next

qwen3.8-flash-next

CHAT ReasoningMultimodal Open-weight

qwen3.8-flash-next (qwen3.8-flash-next) is a chat model from ollama; open-weight; capabilities vision, tools, reasoning; input image, text.

52.089tok / s

Performance

Throughput
52.089 tokens/s
Latency (TTFT)
1.433 s

Cited speed metrics — a reference, verify at the source. Source: Artificial Analysis. Last verified 2026-10-30.

Specifications

Weights
Open-weight
Input modalities
image text

Capabilities

vision tools reasoning

Provenance

artificial-analysisollama-library
Last verified: 2026-10-30

Related models

mistral-large-4
mistral-large-4
ollama · CHAT
deepseek-v3.1
deepseek-v3.1
ollama · CHAT
mistral-large-3
mistral-large-3
ollama · CHAT
devstral-2
devstral-2
ollama · CHAT
mistral-small3.2
mistral-small3.2
ollama · CHAT
devstral-small-2
devstral-small-2
ollama · CHAT

Markdown · Vendor JSON · Full catalog · All ollama models