moonshotai
Kimi-Dev-72B
72.7B parameters · Base · Kimi family
Recommended download
Which version should I download?
Default pick: GGUF · IQ4_XS — Unsloth IQ4_XS quant of Kimi-Dev-72B (72.706B dense) — compact low-bit option. MIT.
Set your rig to confirm it fits and to see if a higher-quality quant runs fully on your hardware.
| Format | Level | Size | Verdict | Est. speed | Quality note | Swarm | Download |
|---|---|---|---|---|---|---|---|
| GGUF | IQ4_XS | 37.02 GB | Set your rig | — | Unsloth IQ4_XS quant of Kimi-Dev-72B (72.706B dense) — compact low-bit option. MIT. | 2S / 0L webseed OK | |
| GGUF | UD-Q5_K_XL | 50.42 GB | Set your rig | — | Unsloth UD-Q5_K_XL dynamic quant of Kimi-Dev-72B (72.706B dense) — quality step-up. MIT. 2-part split GGUF (load via -00001-of-00002). | 1S / 0L webseed OK |
GGUF · IQ4_XS
37.02 GB
- Est. speed
- —
- Swarm
- 2S / 0L webseed OK
Unsloth IQ4_XS quant of Kimi-Dev-72B (72.706B dense) — compact low-bit option. MIT.
GGUF · UD-Q5_K_XL
50.42 GB
- Est. speed
- —
- Swarm
- 1S / 0L webseed OK
Unsloth UD-Q5_K_XL dynamic quant of Kimi-Dev-72B (72.706B dense) — quality step-up. MIT. 2-part split GGUF (load via -00001-of-00002).
Want a different quant? Request it on the board →
Runs fully on
Green = the model's best quant fits fully in GPU/unified memory at 8K context. Tap a card for its full "what runs on it" page.
Context
Advertised 128k · no independent evidence yet
No independent long-context evidence has been graded for this model yet — the advertised window above is the maintainer's number, not a usable-context claim.
Run it
Runtime completeness (IQ4_XS torrent): llama.cpp ✅ Ollama – vision sidecar –
- – Ollama — runs the GGUF directly; no Modelfile bundled
- – vision sidecar — not a vision model
Context / KV 8,192 tokens · FP16 set above the quant table
Generic commands (no rig set). GPU-offload values assume the model fits on your GPU — set your rig for values tuned to your hardware.
llama-server -m Kimi-Dev-72B-IQ4_XS.gguf -c 8192 -ngl 999
Use llama-cli in place of llama-server for a one-shot prompt.
FROM ./Kimi-Dev-72B-IQ4_XS.gguf
PARAMETER num_ctx 8192
PARAMETER num_gpu 999
PARAMETER stop "<|im_end|>"
# Chat template: Ollama uses the template embedded in the GGUF (no TEMPLATE directive needed).
ollama create moonshotai-kimi-dev-72b -f Modelfile
ollama run moonshotai-kimi-dev-72b
GGUF is not a first-class vLLM format.
vLLM GGUF support is experimental and single-file only; prefer safetensors/GPTQ/AWQ for production. If you must, pass the .gguf path to `vllm serve` with --load-format gguf on a recent vLLM.
transformers does not load GGUF weights.
GGUF weights run under llama.cpp, Ollama or LM Studio.
Load Kimi-Dev-72B-IQ4_XS.gguf, set the context length to 8192 tokens. Set GPU offload to Max (all layers).
MLX runs MLX-format weights only (Apple Silicon). This quant is a GGUF build.
GGUF weights run under llama.cpp, Ollama or LM Studio.
Technical details
Chat template
{%- if tools %}
{{- '<|im_start|>system\n' }}
{%- if messages[0]['role'] == 'system' %}
{{- messages[0]['content'] }}
{%- else %}
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
{%- endif %}
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
{%- for tool in tools %}
{{- "\n" }}
{{- tool | tojson }}
{%- endfor %}
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
{%- else %}
{%- if messages[0]['role'] == 'system' %}
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
{%- else %}
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- for message in messages %}
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
{%- elif message.role == "assistant" %}
{{- '<|im_start|>' + message.role }}
{%- if message.content %}
{{- '\n' + message.content }}
{%- endif %}
{%- for tool_call in message.tool_calls %}
{%- if tool_call.function is defined %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{{- '\n<tool_call>\n{"name": "' }}
{{- tool_call.name }}
{{- '", "arguments": ' }}
{{- tool_call.arguments | tojson }}
{{- '}\n</tool_call>' }}
{%- endfor %}
{{- '<|im_end|>\n' }}
{%- elif message.role == "tool" %}
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
{{- '<|im_start|>user' }}
{%- endif %}
{{- '\n<tool_response>\n' }}
{{- message.content }}
{{- '\n</tool_response>' }}
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
{{- '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|im_start|>assistant\n' }}
{%- endif %}
Stop strings
<|im_end|>
Evidence & provenance
Source
- Revision pin
-
8791d7981945752a51f692d66f2bbfb3573c9722 - Manifest
- Present
License
- Name
- mit
- Commercial use
- yes
- Access
- Open
File hashes (SHA-256)
-
kimi-dev-72b-iq4-xs/Kimi-Dev-72B-IQ4_XS.gguf
36b3b5988c5afa6d0ed853deec815b18967312b4e10cdf3c1415d3799eb6ca6b -
kimi-dev-72b-iq4-xs/LICENSE
90ea60983c7da1b06860cd23475bd06fef3d951f8f76ac698fa609445c4bbf11 -
kimi-dev-72b-iq4-xs/README.md
91cc7034a24a788f842590f71019941a8489ddd6791e0a9c349a5be18b7f38c2 -
kimi-dev-72b-ud-q5-k-xl/Kimi-Dev-72B-UD-Q5_K_XL-00001-of-00002.gguf
2823f45ecb6c600b63c777cb8e450db6995bab587182a46beb84a36a4eb6a8a9 -
kimi-dev-72b-ud-q5-k-xl/Kimi-Dev-72B-UD-Q5_K_XL-00002-of-00002.gguf
9a506633e802c8a271c31449073fe1e8de3896c8c9b2655359f78587bad3cfa4 -
kimi-dev-72b-ud-q5-k-xl/LICENSE
90ea60983c7da1b06860cd23475bd06fef3d951f8f76ac698fa609445c4bbf11 -
kimi-dev-72b-ud-q5-k-xl/README.md
91cc7034a24a788f842590f71019941a8489ddd6791e0a9c349a5be18b7f38c2
Explore further
Appears in
Get an email when a better quant fits your rig.
Set your rig once; we'll alert you when a new or better-fitting build lands.
Performance reports
Real-world throughput reported by the community (and scraped sources).
Community
Reviews, sampler presets and community runtime reports. Be the first to contribute.
Community runtime reports
Unofficial, community-submitted "it loads for me" reports. These are not the official verified-working badge — an admin reviews reports before anything is marked officially verified.
Log in to report whether a quant loads in your runtime.
No community reports yet.