Matching posts

Matching terms are highlighted

Strata local four-model test: V4.1 Flash best at long context but slow

Switching four local models in Strata on the same task, the tester found DeepSeek V4.1 Flash strongest on long text and instructions but slow, while Qwen3.8 Coder was fastest at code but broke on Japanese.

deepseek-v4.1@yutacar　Filed in No.020

14 hours agoCopy original

DeepSeek V4.1 Flash Max vs Qwen 4 Kerria on a one-shot 3D pelican scene

…Flash Max Vs Qwen 4 kerria(27B) 一次过生成的 3D 鹈鹕四季骑行对比： 场景细节还是Deepseek V4.1 Flash Max 更好，会随四季变化而变化，自行车…

deepseek-v4.1@leo114119　Filed in No.020

19 hours agoCopy original

POST

DeepSeek V4.1 Flash 2.25-bit GGUF benchmarked against official API

ISTA-DASLab's GSQ-RCO GGUF at 2.25 bits per weight passed 1.1M Hugging Face downloads, and someone benchmarked it head-to-head against the official API as the local-cloud gap narrows.

deepseek-v4.1@DanteMMartin　Filed in No.020

22 hours agoCopy original

Three DeepSeek V4.1 Flash recipes compared on 4x DGX Spark: knapcio prefill ~23% faster

Under TP4 ring, 256K input and thinking on, the knapcio SGLang recipe matched MiaAI's SGLang decode and was about 23% faster in prefill, while the TensorFold build lagged.

deepseek-v4.1@masa_ai_labo　Filed in No.020

10 hours agoCopy original

Four-model comparison: pixel Hello Kitty walking animation

The author asked GPT 6.1 Terra, DeepSeek V4.1 Flash, GPT 6.1 Sol and Muse Wonder for the same animation, praising Terra as fast, cheap and good.

deepseek-v4.1@ann_nnng　Filed in No.020

23 hours agoCopy original

Which metric actually matters when comparing LLMs like DeepSeek V4.1

The author argues token prices, benchmark scores and speed don't capture the real cost of a verified working deliverable, using a bridge-steel analogy and calling for cost-per-verified-task comparisons.

deepseek-v4.1@TugserOkur　Filed in No.020

18 hours agoCopy original

POST

Hands-on: DeepSeek V4.1 Flash wins, but MiniMax M3.1 Flash is more fun to use

A user says DeepSeek won the comparison, but both MiniMax M3.1 Flash and DeepSeek V4.1 Flash 1017 are cool and neither run was perfect; MiniMax feels more fun and they plan to test its code cloud and remote control.

minimax-m3.1@Chris_Wozniczek　Filed in No.021

16 hours agoCopy original

POST

OpenRouter pricing: DeepSeek V4.1 Flash at $0.14/$0.42 per 1M tokens

The author explains why output tokens cost 3–5x input using OpenRouter prices, listing DeepSeek V4.1 Flash at $0.14/$0.42 versus Opus 5.5 at $4/$20.

deepseek-v4.1@KenTheRogers　Filed in No.020

15 hours agoCopy original

POST

Four-model task comparison: V4.1 Flash 50 min, 257K tokens, $0.36

On one task, Opus 5.5 took 30 minutes, GPT-6.1 Sol 10 minutes, Grok 4.7 41 minutes for $3.58, while DeepSeek V4.1 Flash 1017 took 50 minutes, 257K output tokens, for $0.36.

deepseek-v4.1@maker_evan　Filed in No.020

9 hours agoCopy original

Kimi K3.1 Pro vs DeepSeek V4.1 Flash: 46.0 vs 32.5 at best settings

An updated comparison video puts Kimi K3.1 Pro at 46.0 versus DeepSeek V4.1 Flash 1017 at 32.5 under best settings.

deepseek-v4.1@AIcurvewars　Filed in No.020

9 hours agoCopy original

Showing10of60posts

10 per batch

Keep scrolling to reveal posts 11–20

Showing the first 60 matches. Narrow the query with a model name or tag to find more specific results.