selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

meituan-longcat logo

LongCat-2.5

meituan-longcat·Instruct·released 4 Nov 2026

MIT1.78TMoE512K ctx ≈1070 GB
Your GPU
hf download meituan-longcat/LongCat-2.5
Setup ↓

LongCat-2.5 is a native multimodal MoE model for long-horizon agentic tasks, with 1.6 trillion total parameters and approximately 48 billion activated per token.

Notify me when

How much VRAM does LongCat-2.5 need?

At Q4_K_M LongCat-2.5 needs about 1070 GB with an 8K context (1070 GB at Q4, 3496 GB at full precision). Pick your GPU to see what fits and how fast it runs.

--vram
any
--gpus
--quant

Needs: ≈1070 GB · Q4_K_M · 8K context — Pick a GPU to check the fit.

Change quant, context or KV cache to compare
Advanced: context 8K · KV cache 16-bit
Context
KV cache

Smallest GPU for each quant and context (KV cache 16-bit)

Quantisation8K16K32K64K128K512K
Q3_K_M
Q4_K_M
Q5_K_M
Q6_K
Q8_0
FP16

≤16 GB card24–32 GB48–96 GBmore

QuantisationQualityWeightsKV cacheTotal
Q2_KHeavy lossSmallest, noticeably worse qualityHeavy loss545 GB 14 GB≈587 GB
Q3_K_MNoticeable lossSmall, some quality lossNoticeable loss810 GB 14 GB≈865 GB
Q4_K_MrecommendedSmall lossRecommended default for local useSmall loss1005 GB 14 GB≈1070 GB
Q5_K_MNear-losslessNear-lossless for most tasksNear-lossless1179 GB 14 GB≈1253 GB
Q6_KNear-losslessPractically losslessNear-lossless1365 GB 14 GB≈1448 GB
Q8_0LosslessLossless in practice, twice the size of Q4Lossless1761 GB 14 GB≈1864 GB
FP16 / BF16LosslessFull precision, as releasedLossless3315 GB 14 GB≈3496 GB

Estimates for 8K tokens of context: weights + KV cache + runtime overhead. All experts stay in memory, but only the active ones are read per token. Speed assumes memory-bound decoding at your GPU’s bandwidth. Pick a GPU above and the fit column checks every row against it.

How to pick a quant

Take the biggest quant that fits with room left for context. Q4_K_M is the usual sweet spot. Below Q4 quality drops fast, above Q6 you mostly pay memory for nothing. Big models (70B+, large MoE) tolerate low quants better than small ones.

  • LosslessF16, Q8_0
  • Near-losslessQ6_K, Q5_K_M
  • Small lossQ5_K_S, Q4_K_M, IQ4_NL, IQ4_XS, Q4_K_S
  • Noticeable lossQ4_0, Q3_K_L, Q3_K_M, IQ3_M
  • Heavy lossIQ3_XXS, Q3_K_S, IQ2_M, Q2_K

Typical quality loss, not measured per model. Tiers come from KL divergence against FP16 on Llama 3 8B: llama.cpp perplexity README: LLaMA 3 8B scoreboard (KLD and ΔPPL vs FP16, Wikitext-2); llama.cpp quantize tool: ΔPPL per quant type @ Llama-3-8B

How much context fits?

Model quant
KV cache

At 8K context, Q4_K_M needs ≈1070 GB(1005 GB weights + 14 GB KV cache + 51 GB overhead). Pick a GPU above to see how much context fits.

050010001500200025001K2K4K8K16K32K64K128K256K512KGB

Weights + overheadKV cache

Speed vs quality per quant

Smaller quants run faster and fit in less memory, but lose quality.

Q2_KQ3_K_MQ4_K_MQ5_K_MQ6_KQ8_0F16

Fits in VRAMTight fitCPU offload✕ won't runQuality is typical KL divergence vs FP16, not measured for this model.

Real-world speed of LongCat-2.5

Tokens per second measured by people running it at home. A GPU shows a median once 3 reports agree on the same setup. Reports far from our estimate wait for a review. Measure yours with llama-bench →

No medians yet. Be one of the first 3 to report a setup.

All reports

Run LongCat-2.5 locally

No runtime support recorded yet. Most models also run through Hugging Face Transformers.

About LongCat-2.5

LongCat-2.5 is a native multimodal MoE model for long-horizon agentic tasks, with 1.6 trillion total parameters and approximately 48 billion activated per token. Building on LongCat-2.0, it combines visual understanding with agentic coding for complex codebase development, full-project builds, creative design, and 3D tasks. Long-sequence training, large-scale RL, multi-teacher learning, and infrastructure optimizations on domestic AI accelerators underpin these capabilities. • Native Visual Modeling: Building on LongCat-Next, native-resolution visual features are converted into discrete tokens and jointly aligned with text in a shared semantic space. • Long-Horizon Agentic RL: Training combines real-world engineering tasks and reproducible agent failures with efficient rollout strategies and safeguards against reward hacking, improving reliable end-to-end task execution. • Multi-Teacher Learning: Specialized agent, reasoning, and interaction teachers guide the model through full-vocabulary KL distillation and Tree Attention, strengthening multi-turn execution, reasoning, instruction following, and safety. • Efficient Long-Context Training: Supernode-aware parallelism, efficient sharding, and communication–computation overlap improve training efficiency, achieving 86% higher per-device throughput than the DDP baseline in reported long-sequence SFT tasks.

Full model card on Hugging Face →

Alternatives to LongCat-2.5

All alternatives →
moonshotai logo

Kimi-K3

moonshotai·Vision

≈1701 GB

Kimi K3 is an open-weight, native multimodal agentic model and our most capable model to date. It is a 2.8T-parameter model built on Kimi Delta Attention (KDA) and Attention Residuals (AttnRes), with native vision capabilities and a 1-million-token context window.

2.78T1M ctx kimi-k3
731KJun 2026ollama
thinkingmachines logo

Inkling

thinkingmachines·Vision

≈567 GB

Inkling is a general-purpose multimodal model that accepts text, image and audio inputs and generates text outputs. It is intended for use in English and other languages, and across multiple coding languages.

952BA18.1B1M ctx Apache 2.0
1.2MJul 2026gguf
moonshotai logo

Kimi-K3.1-Pro

moonshotai·Vision

≈1701 GB

Kimi K3.1 Pro is an open-weight, natively multimodal agentic model, and our most capable 3T-class model to date. Post-trained from Kimi K3 with large-scale joint reinforcement learning across hundreds of downstream domains, it is the first model in the K3.1 series.

2.78T1M ctx kimi-k3.1-pro
68KNov 2026gguf
moonshotai logo

Kimi-K2.7-Code

moonshotai·Vision

≈632 GB

Kimi K2.7 Code is a coding-focused agentic model built upon Kimi K2.6. With substantial improvements on real-world long-horizon coding tasks, it strengthens end-to-end task completion across complex software engineering workflows while improving token efficiency, reducing thinking-token usage by…

1.03TA33.3B256K ctx modified-mit
324KJun 2026ollama
deepseek-ai logo

DeepSeek-V4.1-Flash

deepseek-ai·Vision

≈454 GB

We introduce DeepSeek-V4.1-Flash, a multimodal Mixture-of-Experts (MoE) model with 552B backbone parameters and support for contexts of up to one million tokens. The model natively processes images and text, and generates text autoregressively.

763BA188B1M ctx MIT
1.3MSept 2026gguf
moonshotai logo

Kimi-K2.6

moonshotai·Vision

≈632 GB

Kimi K2.6 is an open-source, native multimodal agentic model that advances practical capabilities in long-horizon coding, coding-driven design, proactive autonomous execution, and swarm-based task orchestration.

1.03TA33.3B256K ctx modified-mit
198.2KApr 2026ollama

LongCat-2.5 FAQ

How much VRAM does LongCat-2.5 need?
About 1070 GB at Q4_K_M with an 8K context. Q8_0 needs about 1864 GB and full precision about 3496 GB. Longer contexts need more memory for the KV cache.
Can LongCat-2.5 run on a consumer GPU?
Not comfortably on a single one: it needs about 1070 GB at Q4. Split it over several GPUs, use a large unified-memory machine, or offload part of it to system RAM.
Can I use LongCat-2.5 commercially?
Yes. It is released under MIT. Permissive: do almost anything as long as you keep the copyright notice.
What is the context length of LongCat-2.5?
524,288 tokens (512K). The full window needs far more memory than an 8K context.

Data from Hugging Face, the model card and public leaderboards. Memory and speed figures are estimates; real numbers depend on the runtime, context length and drivers. Always check the licence yourself before commercial use.