Qwen
Qwen3-Coder-30B-A3B-Instruct
30.5B parameters · mixture-of-experts · Instruct · Qwen3 family
Recommended download
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.
| Format | Level | Size | Verdict | Est. speed | Quality note | Swarm | Download |
|---|---|---|---|---|---|---|---|
| GGUF | IQ4_XS | 15.25 GB | Set your rig | — | Smallest solid 4-bit — a bit smaller than Q4_K_M with slightly lower quality. | 2S / 0L webseed OK | |
| GGUF | Q4_K_M | 17.28 GB | Set your rig | — | Balanced size/quality — good default. | 2S / 0L webseed OK | |
| GGUF | Q8_0 | 30.25 GB | Set your rig | — | Unsloth Q8_0 quant of Qwen3-Coder-30B-A3B-Instruct (30.5B-A3B MoE) — high-quality option. Apache-2.0. | 2S / 0L webseed OK |
GGUF · IQ4_XS
15.25 GB
- Est. speed
- —
- Swarm
- 2S / 0L webseed OK
Smallest solid 4-bit — a bit smaller than Q4_K_M with slightly lower quality.
GGUF · Q4_K_M
17.28 GB
- Est. speed
- —
- Swarm
- 2S / 0L webseed OK
Balanced size/quality — good default.
GGUF · Q8_0
30.25 GB
- Est. speed
- —
- Swarm
- 2S / 0L webseed OK
Unsloth Q8_0 quant of Qwen3-Coder-30B-A3B-Instruct (30.5B-A3B MoE) — high-quality option. Apache-2.0.
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 256k · usable ≈ 256k (reported — model card)
How we know
Evidence grade: reported — a maintainer claim with no independent evaluation.
- Qwen3-Coder-30B-A3B-Instruct model card — observed Jul 18, 2026
- Qwen3-Coder release blog — observed Jul 18, 2026
Card/blog: native 262,144, ~1M via YaRN. No long-context eval published for this model (sibling 30B-A3B-Instruct-2507 has RULER, but is a different model).
Reviewed on Jul 18, 2026.
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 Qwen3-Coder-30B-A3B-Instruct-IQ4_XS.gguf -c 8192 -ngl 999
Use llama-cli in place of llama-server for a one-shot prompt.
FROM ./Qwen3-Coder-30B-A3B-Instruct-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
PARAMETER repeat_penalty 1.05
# Chat template: Ollama uses the template embedded in the GGUF (no TEMPLATE directive needed).
ollama create qwen-qwen3-coder-30b-a3b-instruct -f Modelfile
ollama run qwen-qwen3-coder-30b-a3b-instruct
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-Coder-30B-A3B-Instruct-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
{% macro render_extra_keys(json_dict, handled_keys) %}
{%- if json_dict is mapping %}
{%- for json_key in json_dict if json_key not in handled_keys %}
{%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %}
{{- '\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }}
{%- else %}
{{-'\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}
{%- endif %}
{%- endfor %}
{%- endif %}
{% endmacro %}
{%- if messages[0]["role"] == "system" %}
{%- set system_message = messages[0]["content"] %}
{%- set loop_messages = messages[1:] %}
{%- else %}
{%- set loop_messages = messages %}
{%- endif %}
{%- if not tools is defined %}
{%- set tools = [] %}
{%- endif %}
{%- if system_message is defined %}
{{- "<|im_start|>system\n" + system_message }}
{%- else %}
{%- if tools is iterable and tools | length > 0 %}
{{- "<|im_start|>system\nYou are Qwen, a helpful AI assistant that can interact with a computer to solve tasks." }}
{%- endif %}
{%- endif %}
{%- if tools is iterable and tools | length > 0 %}
{{- "\n\n# Tools\n\nYou have access to the following functions:\n\n" }}
{{- "<tools>" }}
{%- for tool in tools %}
{%- if tool.function is defined %}
{%- set tool = tool.function %}
{%- endif %}
{{- "\n<function>\n<name>" ~ tool.name ~ "</name>" }}
{%- if tool.description is defined %}
{{- '\n<description>' ~ (tool.description | trim) ~ '</description>' }}
{%- endif %}
{{- '\n<parameters>' }}
{%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}
{%- for param_name, param_fields in tool.parameters.properties|items %}
{{- '\n<parameter>' }}
{{- '\n<name>' ~ param_name ~ '</name>' }}
{%- if param_fields.type is defined %}
{{- '\n<type>' ~ (param_fields.type | string) ~ '</type>' }}
{%- endif %}
{%- if param_fields.description is defined %}
{{- '\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}
{%- endif %}
{%- set handled_keys = ['name', 'type', 'description'] %}
{{- render_extra_keys(param_fields, handled_keys) }}
{{- '\n</parameter>' }}
{%- endfor %}
{%- endif %}
{% set handled_keys = ['type', 'properties'] %}
{{- render_extra_keys(tool.parameters, handled_keys) }}
{{- '\n</parameters>' }}
{%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}
{{- render_extra_keys(tool, handled_keys) }}
{{- '\n</function>' }}
{%- endfor %}
{{- "\n</tools>" }}
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
{%- endif %}
{%- if system_message is defined %}
{{- '<|im_end|>\n' }}
{%- else %}
{%- if tools is iterable and tools | length > 0 %}
{{- '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- for message in loop_messages %}
{%- if message.role == "assistant" and message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
{{- '<|im_start|>' + message.role }}
{%- if message.content is defined and message.content is string and message.content | trim | length > 0 %}
{{- '\n' + message.content | trim + '\n' }}
{%- 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<function=' + tool_call.name + '>\n' }}
{%- if tool_call.arguments is defined %}
{%- for args_name, args_value in tool_call.arguments|items %}
{{- '<parameter=' + args_name + '>\n' }}
{%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
{{- args_value }}
{{- '\n</parameter>\n' }}
{%- endfor %}
{%- endif %}
{{- '</function>\n</tool_call>' }}
{%- endfor %}
{{- '<|im_end|>\n' }}
{%- elif message.role == "user" or message.role == "system" or message.role == "assistant" %}
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
{%- elif message.role == "tool" %}
{%- if loop.previtem and loop.previtem.role != "tool" %}
{{- '<|im_start|>user\n' }}
{%- endif %}
{{- '<tool_response>\n' }}
{{- message.content }}
{{- '\n</tool_response>\n' }}
{%- if not loop.last and loop.nextitem.role != "tool" %}
{{- '<|im_end|>\n' }}
{%- elif loop.last %}
{{- '<|im_end|>\n' }}
{%- endif %}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|im_start|>assistant\n' }}
{%- endif %}
Sampling defaults
- top_k
- 20
- top_p
- 0.8
- temperature
- 0.7
- repetition_penalty
- 1.05
Stop strings
<|im_end|>
<|endoftext|>
Evidence & provenance
Source
- Revision pin
-
b2cff646eb4bb1d68355c01b18ae02e7cf42d120 - Manifest
- Present
License
- Name
- apache-2.0
- Commercial use
- yes
- Access
- Open
File hashes (SHA-256)
-
qwen3-coder-30b-a3b-instruct-iq4-xs/LICENSE
832dd9e00a68dd83b3c3fb9f5588dad7dcf337a0db50f7d9483f310cd292e92e -
qwen3-coder-30b-a3b-instruct-iq4-xs/Qwen3-Coder-30B-A3B-Instruct-IQ4_XS.gguf
26cd4fef3ada9de84c6c59c4b93f9bc5df4d69a71e18cfe8a17369c2f8374ce7 -
qwen3-coder-30b-a3b-instruct-iq4-xs/README.md
35a481e3814ea1679eb2b10c2c79f9ffdb554d324ce9a246f28a67ba7530be63 -
qwen3-coder-30b-a3b-instruct-q4-k-m/LICENSE
832dd9e00a68dd83b3c3fb9f5588dad7dcf337a0db50f7d9483f310cd292e92e -
qwen3-coder-30b-a3b-instruct-q4-k-m/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M.gguf
fadc3e5f8d42bf7e894a785b05082e47daee4df26680389817e2093056f088ad -
qwen3-coder-30b-a3b-instruct-q4-k-m/README.md
35a481e3814ea1679eb2b10c2c79f9ffdb554d324ce9a246f28a67ba7530be63 -
qwen3-coder-30b-a3b-instruct-q8-0/LICENSE
832dd9e00a68dd83b3c3fb9f5588dad7dcf337a0db50f7d9483f310cd292e92e -
qwen3-coder-30b-a3b-instruct-q8-0/Qwen3-Coder-30B-A3B-Instruct-Q8_0.gguf
4ff1cff607804037bf6d2168249c570baa4e1621292b159c0e06591e0d7c3066 -
qwen3-coder-30b-a3b-instruct-q8-0/README.md
35a481e3814ea1679eb2b10c2c79f9ffdb554d324ce9a246f28a67ba7530be63
Explore further
Appears in
Also consider
Local alternative to
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.