No — not on this device

Kimi K2.6 1T-A32B at Q4_K_M needs 578.6 GB against 96.0 GB usable, and the shortfall of 482.6 GB is more than 256 GB of system RAM can cover at a tolerable speed. A smaller sibling or a lower quantisation is the honest answer here.

Does not fit 8K context Q4_K_M · 577.5 GB Modified MIT Released 20 Apr 2026 Not in the Ollama library

The open coding-agent benchmark leader of spring 2026 (80.2 SWE-bench). A 512 GB Mac Studio pair, or a ceiling.

Hardware requirements What hardware do I need to run Kimi K2.6 1T-A32B? →

No single GPU or Mac in the catalogue holds it at Q4_K_M — the page says what comes closest. Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.

The VRAM budget

weights 577.5 GB
Weights 577.5 GB KV cache @ 8K 0.54 GB Runtime overhead 0.6 GB Over budget 482.6 GB past 96.0 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
Q8_0 1016.2 GB 1017.4 GB — ~2.2 −0.1% ppl 921.4 GB over
Q6_K 784.3 GB 785.4 GB — ~2.9 −0.4% ppl 689.4 GB over
Q5_K_M 677.9 GB 679.0 GB — ~3.4 −0.8% ppl 583.0 GB over
Q4_K_M 577.5 GB 578.6 GB — ~4.0 −1.9% ppl 482.6 GB over
Q3_K_M 467.5 GB 468.6 GB — ~4.9 −5.4% ppl 372.6 GB over
Q2_K 400.5 GB 401.7 GB — ~5.7 −15% ppl 305.7 GB over

Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it. This model uses multi-head latent attention, so its cache is a compressed latent rather than full K and V.

How to run it

terminal
$ llama-server \
    -hf moonshotai/Kimi-K2.6:Q4_K_M \
    -c 8192 -ngl 10

The engine underneath most of the others. Every knob is exposed. More on llama.cpp.

01Download is 577.5 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.
02The GPU shares one pool with the operating system, and these numbers count about 96.0 GB of 128 GB as its share. Under Linux the GPU can usually address more than that, so treat the verdict as conservative.
03If it falls back to CPU silently, drop the context first, then step down a quantisation.
See all models for this rig Compare with another model

Related models on a DGX Spark · 128 GB

ModelTotalTok/s est.
Kimi K3 2.8T-A104B
2780B MoE · same family
Q4_K_M · 1564.0 GB — Won't fit
GLM-5.2 744B-A40B
753B MoE · similar size
Q4_K_M · 424.7 GB — Won't fit
GLM-5.3 744B-A40B
753B MoE · similar size
Q4_K_M · 424.7 GB — Won't fit
DeepSeek-R1 671B
671B MoE · similar size
Q4_K_M · 378.4 GB — Won't fit
DeepSeek V4 Pro 1.6T-A49B
1650B MoE · similar size
Q4_K_M · 928.9 GB — Won't fit
DeepSeek V4.1 Flash 552B-A16B
552B MoE · similar size
Q4_K_M · 311.0 GB — Won't fit
Qwen3.8 2.4T-A95B
2446B MoE · similar size
Q4_K_M · 1376.7 GB — Won't fit

Every model against the DGX Spark · 128 GB →

Kimi K2.6 1T-A32B on other hardware

DeviceTotalTok/s est.
GeForce RTX 4060 Laptop
7.0 GB usable · 256 GB/s
578.6 GB — Won't fit
GeForce RTX 3060 12 GB
10.6 GB usable · 360 GB/s
578.6 GB — Won't fit
M4 · 16 GB
10.7 GB usable · 120 GB/s
578.6 GB — Won't fit
GeForce RTX 4090
22.4 GB usable · 1008 GB/s
578.6 GB — Won't fit
Radeon RX 7900 XTX
22.4 GB usable · 960 GB/s
578.6 GB — Won't fit
M3 Max · 64 GB
48.0 GB usable · 400 GB/s
578.6 GB — Won't fit

All 114 devices, by tier →