FareedKhan-dev /kimi-k3-in-c
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
★ 12,133⑂ 1,876👁 105⑃ 96● 19▤ 4
More from this author
+65
Daily
+769
Weekly
+3,123
Monthly
12,133
stars
1,876
forks
105
watchers
96
prs
19
issues
4
releases
README
kimi-k3-in-c
A 2.78-trillion-parameter model. One CPU. 8 GB of RAM.
Kimi K3 inference in portable C99.No BLAS. No framework. No GPU.
2.78Tparameters
1.56 TBcheckpoint on disk
8.24 GBpeak RSS, measured
176 KBthe whole engine
0GPUs
The same 2.78-trillion-parameter model, the same answer, on whatever machine you own.More memory only buys speed:
the machine you have
RAM
time per token
what is going on
an ordinary laptop
8 GB
26.5 s
the whole model streams off the disk on every step
a high-end laptop
32 GB
24.2 s
some of the model now sits in memory
a desktop
64 GB
19.8 s
more of it sits in memory
a heavy workstation
128 GB+
5.6 s
the model fits entirely in memory, the disk wait is gone
Same short prompt at every size, and the output is byte-identical from the smallest machine to the largest; only the clock changes. One machine, 124 cores, fast NVMe drive: the first three rows still read the model from disk each step, so a slower drive is slower there, while the 128 GB+ row keeps everything in memory and no longer waits on the disk. On that same machine v1.0.0 made the math per token about 8× lighter, a follow-up question in a chat 3.9× faster, and long prompts about half as costly. (A token is roughly a short word-piece; the two runnable demos below are the original captures on a slower drive, so their clock reads a little higher.) Full data in docs/data/.
I am open to AI research roles and PhD positions. CV.
The macOS, Windows and NEON ports, chat mode, the ultra preset, the faster MXFP4 kernels, cgroup-aware memory admission and a long list of fixes, most of 2.0.0 among them, came from the people below. Who did what.
console
$ ./bin/k3 ~/k3model --trunk ~/k3trunk --preset laptop \
--tok ~/k3model --prompt "The capital of France is" --gen 8 --incremental
--- generated text ---
Paris.",
+ "The Eiffel
----------------------
8 tokens in 261.5 s, 32.69 s/token average
PEAK RSS for the whole run: 8.24 GB
Slow, and answering correctly, in 8.24 GB, from a checkpoint of 1.56 TB. This particular
batch command deliberately asks for a raw continuation. The official Kimi K3 checkpoint
is also chat-capable; use the XTML REPL below when you want answers and multi-turn history.
Give the same batch request more memory and the answer does not change, only the clock:
console
$ ./bin/k3 ~/k3model --trunk ~/k3trunk --preset server \
--tok ~/k3model --prompt "def fibonacci(n):" --gen 28 --incremental
--- generated text ---
if n [prompt] [memory] [generation] [diagnostics]
is the directory holding the .safetensors shards. It is required for any
run, but --help, --version and --list-presets work without it:
bash
./bin/k3 --help
./bin/k3 --version
./bin/k3 --list-presets
Prompt options
Outside --chat, exactly one of these is required. Passing none, or more than one, is a
usage error (exit 2).
| flag | argument | |
|---|---|---|
| --proTop issues
#3Support for Quantized / Storage-Efficient Kimi K3 Checkpoints7 comments · 2026-08-03#23I have a 5070TI with 16 GB Mem3 comments · 2026-08-10
Latest release
v2.0.0 v2.0.0 2026-11-15Long prompts stop being a one-core job, and a large round of fixes, most of them from outside contributors, makes everything that loads, parses, measures or certifies refuse a wrong input instead of quietly using it. Output is unchanged wherever it was already defined: every oracle gate still matches the PyTorch reference exactly, at any thread count. Compatibility notes, which are why this is 2.0.0: - --save-state files are now version 3, with the header inside the checksum. A version 2 file is refused rather than read; regenerate it with --gen 0 --incremental --save-state. - MLA scratch gr
相关报道 (5)
blog.csdnkimi-k3-in-c 量化实测:为什么拒绝量化 Trunk?int8 损失1%、int4 损失17%的完整数据解析2026-09-01blog.csdnKimi K3 开放权重全景解读:首个开源 3T 级多模态模型的架构与本地部署2026-08-12电子工程专辑EE Times China神了,8G 内存能本地跑 Kimi K3 了。。。2026-09-04爱范儿8GB 内存也能跑 Kimi K3?2026 本地部署大模型配置全指南2026-08-05Pasquale PillitteriKimi K3:单颗 CPU、8 GB 内存跑通 2.78 万亿参数2026-08-03
News & coverage (5)
Hacker NewsKimi K3 2.78T on One CPU with 8GB RAM▲ 4 · 0 comments · 2026-08-05Hacker NewsKimi-k3-in-C: A 2.78T-parameter model. No GPU. 8 GB of RAM▲ 2 · 1 comments · 2026-11-03Hacker NewsKimi-k3-in-C, 2.78T-parameter model, one CPU, 8GB RAM▲ 2 · 0 comments · 2026-08-0453aikimi-k3-in-c2026-10-09Pasquale PillitteriKimi K3: 2.78 Trillion Parameters on One CPU, 8 GB RAM2026-08-03