Qwen

Qwen3-30B-A3B-Instruct-2507

Name: Qwen3-30B-A3B-Instruct-2507
Author: Qwen

30.5B parameters · mixture-of-experts · Instruct · Qwen3 family

Mixture-of-experts — what it means for memory & speed → Long context — how it uses memory →

apache-2.0 hash verified source matched revision pinned

Good for: Long context

Which version should I download?

Default pick: GGUF · Q4_K_M — Balanced size/quality — good default.

Set your rig to confirm it fits and to see if a higher-quality quant runs fully on your hardware.

Set your rig

Quantizations

Why these quants? Which quant should I pick? What do these mean?

Format	Level	Size	Verdict	Est. speed	Quality note	Swarm	Download
GGUF	IQ4_XS	15.25 GB	Set your rig	—	Unsloth IQ4_XS quant of Qwen3-30B-A3B-Instruct-2507 (30.5B-A3B MoE) — compact low-bit option. Apache-2.0.	2S / 0L webseed OK	Magnet .torrent
GGUF	Q4_K_M	17.28 GB	Set your rig	—	Balanced size/quality — good default.	2S / 0L webseed OK	Magnet .torrent
GGUF	Q8_0	30.25 GB	Set your rig	—	Unsloth Q8_0 quant of Qwen3-30B-A3B-Instruct-2507 (30.5B-A3B MoE) — high-quality option. Apache-2.0.	2S / 0L webseed OK	Magnet .torrent

GGUF · IQ4_XS

15.25 GB

Set your rig

Est. speed: —
Swarm: 2S / 0L webseed OK

Unsloth IQ4_XS quant of Qwen3-30B-A3B-Instruct-2507 (30.5B-A3B MoE) — compact low-bit option. Apache-2.0.

Magnet .torrent

GGUF · Q4_K_M

17.28 GB

Set your rig

Est. speed: —
Swarm: 2S / 0L webseed OK

Balanced size/quality — good default.

Magnet .torrent

GGUF · Q8_0

30.25 GB

Set your rig

Est. speed: —
Swarm: 2S / 0L webseed OK

Unsloth Q8_0 quant of Qwen3-30B-A3B-Instruct-2507 (30.5B-A3B MoE) — high-quality option. Apache-2.0.

Magnet .torrent

Want a different quant? Request it on the board →

Runs fully on

RTX 5090 · Q4_K_M RTX 4090 · Q4_K_M RTX 3090 · Q4_K_M RTX 3090 Ti · Q4_K_M RTX Pro 6000 Blackwell 96GB · Q8_0

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 256k · usable ≈ 128–256k (measured — RULER)

How we know

Evidence grade: measured — a published evaluation we can cite, with task and length stated.

Qwen3-30B-A3B-Instruct-2507 model card (RULER table) — observed Jul 18, 2026

Model card RULER table (Dual Chunk Attention, 260 samples/length): average 86.8; 82.5 at 256k, 78.4 at 512k, 72.8 at 1000k. Native 262,144; ~1M via documented config.

Reviewed on Jul 18, 2026.

Capabilities (as declared by the maintainer): tool calling

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

Quant

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.

Start the server

llama-server -m Qwen3-30B-A3B-Instruct-2507-IQ4_XS.gguf -c 8192 -ngl 999

Use llama-cli in place of llama-server for a one-shot prompt.

Save as Modelfile next to the GGUF (Modelfile)

FROM ./Qwen3-30B-A3B-Instruct-2507-IQ4_XS.gguf
PARAMETER num_ctx 8192
PARAMETER num_gpu 999
PARAMETER stop "<|im_end|>"
PARAMETER stop "<|endoftext|>"
PARAMETER temperature 0.7
PARAMETER top_p 0.8
PARAMETER top_k 20
# Chat template: Ollama uses the template embedded in the GGUF (no TEMPLATE directive needed).

Create

ollama create qwen-qwen3-30b-a3b-instruct-2507 -f Modelfile

Run

ollama run qwen-qwen3-30b-a3b-instruct-2507

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 Qwen3-30B-A3B-Instruct-2507-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 + '\n\n' }}
    {%- endif %}
    {{- "# 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' }}
    {%- endif %}
{%- endif %}
{%- for message in messages %}
    {%- if message.content is string %}
        {%- set content = message.content %}
    {%- else %}
        {%- set content = '' %}
    {%- endif %}
    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
    {%- elif message.role == "assistant" %}
        {{- '<|im_start|>' + message.role + '\n' + content }}
        {%- if message.tool_calls %}
            {%- for tool_call in message.tool_calls %}
                {%- if (loop.first and content) or (not loop.first) %}
                    {{- '\n' }}
                {%- endif %}
                {%- if tool_call.function %}
                    {%- set tool_call = tool_call.function %}
                {%- endif %}
                {{- '<tool_call>\n{"name": "' }}
                {{- tool_call.name }}
                {{- '", "arguments": ' }}
                {%- if tool_call.arguments is string %}
                    {{- tool_call.arguments }}
                {%- else %}
                    {{- tool_call.arguments | tojson }}
                {%- endif %}
                {{- '}\n</tool_call>' }}
            {%- endfor %}
        {%- endif %}
        {{- '<|im_end|>\n' }}
    {%- elif message.role == "tool" %}
        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
            {{- '<|im_start|>user' }}
        {%- endif %}
        {{- '\n<tool_response>\n' }}
        {{- 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 %}

Sampling defaults

top_k: 20
top_p: 0.8
temperature: 0.7

Stop strings

<|im_end|> <|endoftext|>

Evidence & provenance

Source

Provenance: https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507
Revision pin: 0d7cf23991f47feeb3a57ecb4c9cee8ea4a17bfe
Manifest: Present

License

Name: apache-2.0
Commercial use: yes
Access: Open

How verification works →

File hashes (SHA-256)

qwen3-30b-a3b-instruct-2507-iq4-xs/LICENSE 05cab46843576551502bfdf712f84e93e6e9590d9997306ed4f6635ef82811d9
qwen3-30b-a3b-instruct-2507-iq4-xs/Qwen3-30B-A3B-Instruct-2507-IQ4_XS.gguf bd03aa8b332adb414eb842ec725b4a5dd116b17b57d4e5543ba742587a3c5e21
qwen3-30b-a3b-instruct-2507-iq4-xs/README.md 649af14051755c577335465ff82d258e7c8cbf2e95728892b6276b9f1db6931b
qwen3-30b-a3b-instruct-2507/LICENSE 05cab46843576551502bfdf712f84e93e6e9590d9997306ed4f6635ef82811d9
qwen3-30b-a3b-instruct-2507/Qwen3-30B-A3B-Instruct-2507-Q4_K_M.gguf 6c997b8af17debdfb01d890214400ccbab00db6acc0ba8da5de1cc906c4774d0
qwen3-30b-a3b-instruct-2507/README.md 649af14051755c577335465ff82d258e7c8cbf2e95728892b6276b9f1db6931b
qwen3-30b-a3b-instruct-2507-q8-0/LICENSE 05cab46843576551502bfdf712f84e93e6e9590d9997306ed4f6635ef82811d9
qwen3-30b-a3b-instruct-2507-q8-0/Qwen3-30B-A3B-Instruct-2507-Q8_0.gguf 47514861adaa7ae7f32818fe54595c7cbed2753417ba78df53054fcf7b9dcd88
qwen3-30b-a3b-instruct-2507-q8-0/README.md 649af14051755c577335465ff82d258e7c8cbf2e95728892b6276b9f1db6931b

Explore further

Appears in

What runs on 24 GB of VRAM What runs on 32 GB of VRAM What runs on 48 GB of VRAM What runs on a 36 GB Mac What runs on a 48 GB Mac What runs on a 64 GB Mac

Also consider

Local alternative to

A local alternative to Claude Sonnet →

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.

Set your rig

Performance reports

Real-world throughput reported by the community (and scraped sources).

View performance leaderboard

Community

Reviews, sampler presets and community runtime reports. Be the first to contribute.

Reviews (0)

No reviews yet.

Sampler presets

No presets yet.

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.

No community reports yet.

Recommended download

Quantizations

Runs fully on

Context

Run it

Chat template

Sampling defaults

Stop strings

Evidence & provenance

Source

License

File hashes (SHA-256)

Explore further

Appears in

Also consider

Local alternative to

Performance reports

Reviews (0)

Sampler presets

Community runtime reports