Kimi Linear 48B-A3B Instruct

48B-A3B

Moonshot Kimi Linear

Moonshot's hybrid linear-attention model: 48B total, 3B active, a 1M-token window. Only 7 of its 27 layers keep a growing cache, and those store MLA's compressed vectors, so even the full million tokens needs about 8 GB of cache — the weights, not the context, decide what it runs on. At Q4 a Mac with 48 GB or more runs it comfortably; a 32 GB card holds it only with no room to spare. Sizes below use the calculator's generic rates: no GGUF file size could be checked, and quality loss per level has not been published.

⬇ 193.7K HF downloads♥ 601 likesmoonshotai/Kimi-Linear-48B-A3B-Instruct· stats from 9/30/2026
Pro GPUMac / Apple Silicon

1049K

Max Context

2

Quant Variants

GGUF Q8_0

Best Quality

—

Accuracy Retained

Quantization Variants

Per-quant VRAM, quality loss, and inference speed on RTX 4090

Measured = run on this site · Estimated = not run here: calculated, or a figure this site has not verified · Community = public reports

FormatLevelBPWVRAMPPL LossSpeedSourceActions
GGUFQ4_K_M4.8529.1 GB——Estimated
CalcHF
GGUFQ8_08.551.0 GB——Estimated
CalcHF

Running Kimi Linear 48B-A3B Instruct locally

At Q4_K_M and 4K of context, Kimi Linear 48B-A3B Instruct needs about 30.4 GB — 27.6 GB of weights, 0.03 GB of KV cache and a 2.8 GB activation buffer. The smallest card in this index that clears that comfortably is the A100 40G at 40 GB, and 17 of the 59 cards here do. These are calculated figures, not measurements: the estimate stops counting a card as comfortable at 88% of its VRAM, which is roughly the room a desktop session needs.

What longer context costs

Going from 4K to 32K adds about 0.22 GB, taking the total to 30.7 GB. That is gentler than the parameter count suggests: only 7 of 27 layers keep a KV cache that grows with context, so the cache scales at a fraction of the usual rate. The model's native window is 1M; holding all of it at Q4_K_M would need about 39 GB.

Which build to download

This index only tracks Kimi Linear 48B-A3B Instruct in GGUF, across 2 levels (Q4_K_M, Q8_0). No per-level perplexity sweep has been published for this model, so the quality column is empty rather than estimated — within one model, more bits per weight is the only ordering the data supports. No throughput has been measured for this model on this site's hardware. GGUF runs on llama.cpp and Ollama across NVIDIA, AMD and Apple silicon; AWQ and GPTQ target vLLM on CUDA and ROCm; EXL2 is ExLlamaV2 and CUDA only.

Common questions

How much VRAM does Kimi Linear 48B-A3B Instruct need?
About 30.4 GB at Q4_K_M with 4K of context and batch 1, rising to roughly 30.7 GB at 32K. That figure is weights plus KV cache plus a 10% activation buffer, calculated from the model's architecture rather than measured on a card.
Will Kimi Linear 48B-A3B Instruct run on a 40GB GPU?
Yes — at Q4_K_M and 4K context it needs about 30.4 GB, which leaves 9.6 GB spare on a A100 40G. That is the smallest card in this index that clears it comfortably; 17 of 59 do.
Which quantization of Kimi Linear 48B-A3B Instruct should I use?
No published quality comparison exists for this model, so pick by footprint: Q4_K_M is the level most people run, and a higher bits-per-weight level is more faithful. All 2 levels in the index are Q4_K_M, Q8_0. Note this is a mixture-of-experts model — all parameters must be resident even though only a fraction are active per token, so the memory cost follows the total, not the active count.

Where this model fits

Sized at Q4_K_M with a 4K context window, smallest card first. Comfortable means the estimate uses at most 88% of the memory.

Ships in
GGUF

This page's figures change when the model or the runtime does.Last updated 2026-09-30 RSS → /feed.xml