Unverified50% confidenceFactExact time
Gemma 4 E2B's KV cache capacity is 321,280 tokens, which is 2.6 to 6.3 times that of Granite 3.3 2B (125,184), SmolLM3-3B (120,320), Qwen3-1.7B (100,096), and Qwen3-4B (50,688).
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
单块TPU v5e实测：哪些小模型能与Gemma 4 E2B一战？
Related Entities
Related Claims
Unverifiedclaude-code-local claims to support models including Qwen 3.5 122B (approximately 65 tokens/second), Llama 3.3 70B, and Gemma 4 31B.70% similarUnverifiedEmbedding Gemma 2 outputs 768-dimensional vectors (truncatable to 512, 256, or 128 dimensions), has a context length of 8,192 tokens, supports over 100 languages, and is released under the Apache 2.0 license.65% similarVerifiedGemma 4的1B/2B模型量化后仅需4GB显存即可运行64% similarUnverifiedAfter adopting GQA, Llama 3.3 70B has a KV Cache of approximately 320 KB per token.64% similarUnverifiedQuantizing the KV cache from FP16 to Q4 can achieve approximately 4x VRAM savings at the cost of minimal precision loss.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1014583API
curl https://kongchang.com/api/v1/knowledge/claims/1014583MCP
get_claim(id=1014583)