on main help sign in
docs(readme): move "local models" section to be under "custom providers" (#1402)
commit025d6041ed4d19a884fbf9abb9a1ca59c4282ea9 authorAndrey Nering <andreynering@users.noreply.github.com> dateMon 10 Nov 2025, 13:28 (1 year ago) parent07d5e5e
1 file changed+48−48
README.md+48−48
README.md+48−48
@@ -355,54 +355,6 @@ it creates. You can customize this behavior with the `attribution` option:
355355- `co_authored_by`: When true (default), adds `Co-Authored-By: Crush <crush@charm.land>` to commit messages
356356- `generated_with`: When true (default), adds `💘 Generated with Crush` line to commit messages and PR descriptions
357357
358−### Local Models
359−
360−Local models can also be configured via OpenAI-compatible API. Here are two common examples:
361−
362−#### Ollama
363−
364−```json
365−{
366− "providers": {
367− "ollama": {
368− "name": "Ollama",
369− "base_url": "http://localhost:11434/v1/",
370− "type": "openai-compat",
371− "models": [
372− {
373− "name": "Qwen 3 30B",
374− "id": "qwen3:30b",
375− "context_window": 256000,
376− "default_max_tokens": 20000
377− }
378− ]
379− }
380− }
381−}
382−```
383−
384−#### LM Studio
385−
386−```json
387−{
388− "providers": {
389− "lmstudio": {
390− "name": "LM Studio",
391− "base_url": "http://localhost:1234/v1/",
392− "type": "openai-compat",
393− "models": [
394− {
395− "name": "Qwen 3 30B",
396− "id": "qwen/qwen3-30b-a3b-2507",
397− "context_window": 256000,
398− "default_max_tokens": 20000
399− }
400− ]
401− }
402− }
403−}
404−```
405−
406358### Custom Providers
407359
408360Crush supports custom provider configurations for both OpenAI-compatible and
@@ -521,6 +473,54 @@ To add specific models to the configuration, configure as such:
521473}
522474```
523475
476+### Local Models
477+
478+Local models can also be configured via OpenAI-compatible API. Here are two common examples:
479+
480+#### Ollama
481+
482+```json
483+{
484+ "providers": {
485+ "ollama": {
486+ "name": "Ollama",
487+ "base_url": "http://localhost:11434/v1/",
488+ "type": "openai-compat",
489+ "models": [
490+ {
491+ "name": "Qwen 3 30B",
492+ "id": "qwen3:30b",
493+ "context_window": 256000,
494+ "default_max_tokens": 20000
495+ }
496+ ]
497+ }
498+ }
499+}
500+```
501+
502+#### LM Studio
503+
504+```json
505+{
506+ "providers": {
507+ "lmstudio": {
508+ "name": "LM Studio",
509+ "base_url": "http://localhost:1234/v1/",
510+ "type": "openai-compat",
511+ "models": [
512+ {
513+ "name": "Qwen 3 30B",
514+ "id": "qwen/qwen3-30b-a3b-2507",
515+ "context_window": 256000,
516+ "default_max_tokens": 20000
517+ }
518+ ]
519+ }
520+ }
521+}
522+```
523+
524524## Logging
525525
526526Sometimes you need to look at logs. Luckily, Crush logs all sorts of