Unverified50% confidenceBenchmarkTime unknown
claude-code-local claims to support models including Qwen 3.5 122B (approximately 65 tokens/second), Llama 3.3 70B, and Gemma 4 31B.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/12/2026
First Seen
Valid until: 12/11/2026
Sources
Related Entities
Related Claims
UnverifiedQwen3 在训练时支持长达 128K tokens 的上下文72% similarUnverifiedEarly LLaMA-2 only supported a 4K token context, whereas new-generation models such as DeepSeek-V3 and Qwen2.5 have extended the context to 128K or even longer.71% similarUnverifiedQwen 4B and 7B versions can run smoothly on entry-level graphics cards with 8GB of VRAM such as the RTX 3060.71% similarUnverifiedThe officially supported context length of Gemma 3 12B is 128K tokens, but the default num_ctx in Ollama is only 2048.70% similarUnverifiedThe original Qwen3 model supports a 256K context, but local deployment is limited to 128K due to VRAM constraints70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/917423API
curl https://kongchang.com/api/v1/knowledge/claims/917423MCP
get_claim(id=917423)