MiniMaxAI
MiniMax-M3
427B parameters · mixture-of-experts · reasoning · Base · MiniMax family
Recommended download
Which version should I download?
Default pick: GGUF · UD-Q2_K_XL — Unsloth dynamic 2-bit (UD-Q2_K_XL) — runnable 427B-A23B MoE giant lead (~143 GB, 4 shards; preservation copy). MiniMax Community License: redistributable; downstream commercial use needs Built-with-MiniMax-M3 attribution + notice.
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 | UD-Q2_K_XL | 133.15 GB | Set your rig | — | Unsloth dynamic 2-bit (UD-Q2_K_XL) — runnable 427B-A23B MoE giant lead (~143 GB, 4 shards; preservation copy). MiniMax Community License: redistributable; downstream commercial use needs Built-with-MiniMax-M3 attribution + notice. | 1S / 0L webseed OK |
GGUF · UD-Q2_K_XL
133.15 GB
- Est. speed
- —
- Swarm
- 1S / 0L webseed OK
Unsloth dynamic 2-bit (UD-Q2_K_XL) — runnable 427B-A23B MoE giant lead (~143 GB, 4 shards; preservation copy). MiniMax Community License: redistributable; downstream commercial use needs Built-with-MiniMax-M3 attribution + notice.
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 1M · 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 (UD-Q2_K_XL 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 MiniMax-M3-UD-Q2_K_XL-00001-of-00004.gguf -c 8192 -ngl 999
Use llama-cli in place of llama-server for a one-shot prompt.
FROM ./MiniMax-M3-UD-Q2_K_XL-00001-of-00004.gguf
PARAMETER num_ctx 8192
PARAMETER num_gpu 999
PARAMETER stop "[e~["
PARAMETER temperature 1
PARAMETER top_p 0.95
# Chat template: Ollama uses the template embedded in the GGUF (no TEMPLATE directive needed).
ollama create minimaxai-minimax-m3 -f Modelfile
ollama run minimaxai-minimax-m3
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 MiniMax-M3-UD-Q2_K_XL-00001-of-00004.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
{# ---------- special token variables ---------- #}
{%- set ns_token = ']<]minimax[>[' -%}
{%- set bod_token = ']~!b[' -%}
{%- set bos_token = ']~b]' -%}
{%- set eos_token = '[e~[' -%}
{%- set toolcall_begin_token = ns_token ~ '<tool_call>' -%}
{%- set toolcall_end_token = ns_token ~ '</tool_call>' -%}
{%- set think_begin_token = '<mm:think>' -%}
{%- set think_end_token = '</mm:think>' -%}
{%- set image_token = ']<]image[>[' -%}
{%- set video_token = ']<]video[>[' -%}
{#- Thinking mode: "enabled" / "disabled" / "adaptive" / not defined -#}
{#- Recursive XML renderer for tool_call arguments ======================== -#}
{#- None values are intentionally skipped in mapping iteration so that
`<key>null</key>` (which would round-trip to the literal string "null")
never appears in the rendered tool_call. The convention is: omit the
field entirely. The top-level `_args` loop applies the same rule.
The `val is none` branch below is a safety net only — upstream cleaning
(drop_none_in_tool_arguments) should ensure no None ever reaches here. -#}
{%- macro to_xml(val, ns) -%}
{%- if val is mapping -%}
{%- for k, v in val.items() if v is not none -%}
{{ ns }}<{{ k }}>{{ to_xml(v, ns) }}{{ ns }}</{{ k }}>
{%- endfor -%}
{%- elif val is iterable and val is not string -%}
{%- for item in val -%}
{{ ns }}<item>{{ to_xml(item, ns) }}{{ ns }}</item>
{%- endfor -%}
{%- elif val is none -%}
{#- Should be unreachable when upstream cleaning is applied. -#}
{%- elif val is boolean -%}
{{ val | tojson }}
{%- else -%}
{{ val }}
{%- endif -%}
{%- endmacro -%}
{#- Tool Rendering Functions ============================================== -#}
{%- macro render_tool_namespace(namespace_name, tool_list) -%}
{%- for tool in tool_list -%}
<tool>{{ tool.function | tojson(ensure_ascii=False) }}</tool>
{% endfor -%}
{%- endmacro -%}
{%- macro visible_text(content) -%}
{%- if content is string -%}
{{ content }}
{%- elif content is iterable and content is not mapping -%}
{%- for item in content -%}
{%- if item is mapping and item.type == 'text' -%}
{{- item.text }}
{%- elif item is mapping and item.type == 'image' -%}
{{- image_token }}
{%- elif item is mapping and item.type == 'video' -%}
{{- video_token}}
{%- elif item is string -%}
{{- item }}
{%- endif -%}
{%- endfor -%}
{%- elif content is none -%}
{{- '' }}
{%- else -%}
{{- content }}
{%- endif -%}
{%- endmacro -%}
{#- System Message Construction ============================================ -#}
{%- macro build_system_message(system_message) -%}
{%- if system_message and system_message.content -%}
{{- visible_text(system_message.content) }}
{%- else -%}
{{- 'Your model version is MiniMax-M3, developed by MiniMax. Knowledge cutoff: January 2026. Founded in early 2022, MiniMax is a global AI foundation model company committed to advancing the frontiers of AI towards AGI.' }}
{%- endif -%}
{#- Thinking mode instructions -#}
{{- '\n\n<thinking_instructions>\n' }}
{{- 'You have a thinking capability that allows you to reason step by step before responding. When thinking is enabled, wrap your reasoning in ' ~ think_begin_token ~ think_end_token ~ ' tags before your response. When thinking is disabled, begin your response directly after the ' ~ think_end_token ~ ' prefix. When thinking is adaptive, decide on your own whether to think for the current turn.\n' }}
{%- if thinking_mode is defined -%}
{%- if thinking_mode == "enabled" -%}
{{- 'Current thinking mode: enabled. You MUST think step by step before every response, including after receiving function/tool results.\n' }}
{%- elif thinking_mode == "disabled" -%}
{{- 'Current thinking mode: disabled. Do not output any thinking process.\n' }}
{%- elif thinking_mode == "adaptive" -%}
{{- 'Current thinking mode: adaptive. You are encouraged to think for complex decision-making, multi-step reasoning, or when analyzing function/tool results.\n' }}
{%- endif -%}
{%- else -%}
{{- 'Current thinking mode: adaptive. You are encouraged to think for complex decision-making, multi-step reasoning, or when analyzing function/tool results.\n' }}
{%- endif -%}
{{- '</thinking_instructions>' }}
{%- endmacro -%}
{%- macro build_developer_message(developer_message) -%}
{%- if developer_message and developer_message.content -%}
{{- visible_text(developer_message.content) }}
{%- else -%}
{%- if model_identity is not defined -%}
{%- set model_identity = "You are a helpful assistant." -%}
{%- endif -%}
{{- model_identity }}
{%- endif -%}
{%- endmacro -%}
{#- Main Template Logic ================================================= -#}
{#- Role mapping: root -> system sp (high priority), system/developer -> developer sp (low priority) -#}
{%- set system_message = none -%}
{%- set developer_message = none -%}
{%- set conversation_messages = messages -%}
{%- if messages and messages[0].role == "root" -%}
{%- set system_message = messages[0] -%}
{%- set conversation_messages = messages[1:] -%}
{%- if conversation_messages and conversation_messages[0].role in ["system", "developer"] -%}
{%- set developer_message = conversation_messages[0] -%}
{%- set conversation_messages = conversation_messages[1:] -%}
{%- endif -%}
{%- elif messages and messages[0].role in ["system", "developer"] -%}
{%- set developer_message = messages[0] -%}
{%- set conversation_messages = messages[1:] -%}
{%- endif -%}
{#- Render system sp (higher priority, root role only) -#}
{{- bod_token ~ bos_token ~ 'system' ~ '\n' }}
{{- build_system_message(system_message) }}
{{- eos_token ~ '\n' }}
{#- Render developer sp (lower priority: system/developer role + tools) -#}
{{- bos_token ~ 'developer' ~ '\n' }}
{{- build_developer_message(developer_message) }}
{%- if tools -%}
{{- '\n\n' ~ '# Tools' ~ '\n' ~ 'You may call one or more tools to assist with the user query.\nHere are the tools available in JSONSchema format:' ~ '\n' }}
{{- '\n' ~ '<tools>' ~ '\n' }}
{{- render_tool_namespace("functions", tools) }}
{{- '</tools>' ~ '\n\n' }}
{{- 'To call tools, wrap all invocations in a single ' ~ toolcall_begin_token ~ toolcall_end_token ~ ' block. Parameter values containing nested objects or arrays are recursively expanded into XML elements. Example:\n' }}
{{- '\n' ~ toolcall_begin_token ~ '\n' }}
{{- ns_token + '<invoke name="tool-name-1">' }}
{{- ns_token + '<param-1>value-1' + ns_token + '</param-1>' }}
{{- ns_token + '<param-2>' }}
{{- ns_token + '<item>' }}
{{- ns_token + '<key-a>val-a' + ns_token + '</key-a>' }}
{{- ns_token + '<key-b>val-b' + ns_token + '</key-b>' }}
{{- ns_token + '</item>' }}
{{- ns_token + '</param-2>' }}
{{- ns_token + '</invoke>\n' }}
{{- ns_token + '<invoke name="tool-name-2">' }}
{{- ns_token + '<param-1>value-1' + ns_token + '</param-1>' }}
{{- ns_token + '</invoke>\n' }}
{{- toolcall_end_token }}
{%- endif -%}
{{- eos_token ~ '\n' }}
{#- Render messages -#}
{%- set last_tool_call = namespace(name=none) -%}
{%- for message in conversation_messages -%}
{%- if message.role == 'assistant' -%}
{{- bos_token ~ 'ai' ~ '\n' }}
{%- set reasoning_content = '' %}
{%- set content = visible_text(message.content) %}
{%- if message.reasoning_content is string %}
{%- set reasoning_content = message.reasoning_content %}
{%- else %}
{%- if think_end_token in content %}
{%- set reasoning_content = content.split(think_end_token)[0].strip('\n').split(think_begin_token)[-1].strip('\n') %}
{%- set content = content.split(think_end_token)[-1].strip('\n') %}
{%- endif %}
{%- endif %}
{%- if reasoning_content -%}
{#- Render thinking for every assistant turn (all-turn visible) -#}
{{- think_begin_token ~ reasoning_content ~ think_end_token }}
{%- else -%}
{#- No thinking rendered → prefix with think_end_token -#}
{{- think_end_token }}
{%- endif -%}
{%- if content -%}
{{- content }}
{%- endif -%}
{%- if message.tool_calls -%}
{{- toolcall_begin_token ~ '\n' }}
{%- for tool_call in message.tool_calls -%}
{%- if tool_call.function -%}
{%- set tool_call = tool_call.function -%}
{%- endif -%}
{{- ns_token + '<invoke name="' + tool_call.name + '">' }}
{%- set _args = tool_call.arguments -%}
{%- for k, v in _args.items() if v is not none %}
{{- ns_token + '<' + k + '>' -}}
{{- to_xml(v, ns_token) -}}
{{- ns_token + '</' + k + '>' }}
{%- endfor -%}
{{- ns_token + '</invoke>' ~ '\n' }}
{%- endfor -%}
{{- toolcall_end_token }}
{%- if message.tool_calls[-1].function -%}
{%- set last_tool_call.name = message.tool_calls[-1].function.name -%}
{%- else -%}
{%- set last_tool_call.name = message.tool_calls[-1].name -%}
{%- endif -%}
{%- else -%}
{%- set last_tool_call.name = none -%}
{%- endif -%}
{{- eos_token ~ '\n' }}
{%- elif message.role == 'tool' -%}
{%- if last_tool_call.name is none -%}
{{- raise_exception("Message has tool role, but there was no previous assistant message with a tool call!") }}
{%- endif -%}
{%- if loop.first or (conversation_messages[loop.index0 - 1].role != 'tool') -%}
{{- bos_token ~ 'tool' }}
{%- endif -%}
{{- '\n<response>' }}
{%- if message.content is string -%}
{{- message.content }}
{%- else -%}
{%- for tr in message.content -%}
{%- if tr is mapping and tr.type is defined and tr.type == 'image' -%}
{{- image_token }}
{%- elif tr is mapping and tr.type is defined and tr.type == 'video' -%}
{{- video_token }}
{%- else -%}
{{- tr.output if tr.output is defined else (tr.text if tr.type == 'text' and tr.text is defined else tr) }}
{%- endif -%}
{%- endfor -%}
{%- endif -%}
{{- '</response>' }}
{%- if loop.last or (conversation_messages[loop.index0 + 1].role != 'tool') -%}
{{- eos_token ~ '\n' -}}
{%- endif -%}
{%- elif message.role == 'user' -%}
{{- bos_token ~ 'user' ~ '\n' }}
{{- visible_text(message.content) }}
{{- eos_token ~ '\n' }}
{%- endif -%}
{%- endfor -%}
{#- Generation prompt -#}
{%- if add_generation_prompt -%}
{{- bos_token ~ 'ai' ~ '\n' }}
{%- if thinking_mode is defined and thinking_mode == "disabled" -%}
{{- think_end_token }}
{%- elif thinking_mode is defined and thinking_mode == "adaptive" -%}
{#- adaptive: no prefix, let model decide -#}
{%- elif thinking_mode is defined and thinking_mode == "enabled" -%}
{#- enabled or not defined: default to think -#}
{{- think_begin_token }}
{%- else -%}
{#- adaptive: no prefix, let model decide -#}
{%- endif -%}
{%- endif -%}
Sampling defaults
- top_p
- 0.95
- temperature
- 1
Stop strings
[e~[
Evidence & provenance
Source
- Provenance
- https://huggingface.co/MiniMaxAI/MiniMax-M3
- Revision pin
-
50942730318c7943fe83db7ec8e9f9177ecb1cf8 - Manifest
- Present
License
- Name
- minimax-community
- Commercial use
- unclear
- Access
- Open
- Notes
- MiniMax Community License (bundled verbatim). Grants free non-commercial rights to use/copy/modify/publish/DISTRIBUTE/sublicense -> redistribution permitted (preservation mirror). Commercial use by downstream products requires Built-with-MiniMax-M3 attribution + one-time notice (or written authorization above $20M yearly revenue) to [email protected]; prohibited-uses appendix applies. Verified 2026-07-12.
File hashes (SHA-256)
-
minimax-m3-ud-q2-k-xl/LICENSE
b53f2fdda3049b0e9013207be51efc2d372cda1fcfdd8bb4bb8b22658ca5db9c -
minimax-m3-ud-q2-k-xl/MiniMax-M3-UD-Q2_K_XL-00001-of-00004.gguf
eed1a93ce4df7174594a3f681ae141562d2d6b708b989a4fe19de4cd75cd3268 -
minimax-m3-ud-q2-k-xl/MiniMax-M3-UD-Q2_K_XL-00002-of-00004.gguf
d4a3e10d123a7c761fcaa7c5bcaf72e0861585aa7e2fe90a99f7e1ad4fc1957c -
minimax-m3-ud-q2-k-xl/MiniMax-M3-UD-Q2_K_XL-00003-of-00004.gguf
cc338e328a6cfea8b9e47476cbec5faeceb3bc6497cedc27df9985178d401c07 -
minimax-m3-ud-q2-k-xl/MiniMax-M3-UD-Q2_K_XL-00004-of-00004.gguf
152dafa2f842d36b74491038906e193af00d72098508f34aaba753b4998edb43 -
minimax-m3-ud-q2-k-xl/README.md
ca005ef5e95860af62896c32d20decf9cd74c30ba8c5cf7f18f6fab1f496054a
Explore further
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.