github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 05:05:37 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #7365] Unable to pull IQ4_NL quants from HF #30441

New Issue
Closed
opened 2026-04-22 10:03:42 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-22 10:03:42 -05:00
Owner
Copy Link

Originally created by @Mushoz on GitHub (Oct 25, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7365

What is the issue?

Pulling existing IQ4_NL quants from HF seem to fail:

ollama run hf.co/bartowski/Replete-LLM-V2.5-Qwen-32b-GGUF:IQ4_NL
pulling manifest
Error: pull model manifest: 400: The specified tag is not a valid quantization scheme. Please use another tag or "latest"

Any other quant does work fine.

OS

Docker

GPU

AMD

CPU

AMD

Ollama version

0.3.14

Originally created by @Mushoz on GitHub (Oct 25, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7365 ### What is the issue? Pulling existing IQ4_NL quants from HF seem to fail: ollama run hf.co/bartowski/Replete-LLM-V2.5-Qwen-32b-GGUF:IQ4_NL pulling manifest Error: pull model manifest: 400: The specified tag is not a valid quantization scheme. Please use another tag or "latest" Any other quant does work fine. ### OS Docker ### GPU AMD ### CPU AMD ### Ollama version 0.3.14
GiteaMirror added the bug label 2026-04-22 10:03:42 -05:00
GiteaMirror commented 2026-04-22 10:03:44 -05:00
Author
Owner
Copy Link

@Mushoz commented on GitHub (Oct 25, 2024):

Someone tested it on Discord, and experienced the same issue:

Screenshot From 2024-10-25 21-52-39

<!-- gh-comment-id:2438682066 --> @Mushoz commented on GitHub (Oct 25, 2024): Someone tested it on Discord, and experienced the same issue: ![Screenshot From 2024-10-25 21-52-39](https://github.com/user-attachments/assets/7fe753e0-d728-40cb-85bd-bd91581b97e3)
GiteaMirror commented 2026-04-22 10:03:44 -05:00
Author
Owner
Copy Link

@mxyng commented on GitHub (Oct 25, 2024):

The specified tag is not a valid quantization scheme. Please use another tag or "latest"

This error is not emitted by Ollama nor does Ollama validate quantization based on file name. The upstream, Hugging Face in this case, is refusing to serve the file. I suggest you open the issue with them.

$ curl -vL -H Accept:application/vnd.docker/distribution.manifest.v2+json hf.co/v2/bartowski/Replete-LLM-V2.5-Qwen-32b-GGUF/manifests/IQ4_NL
* Host hf.co:80 was resolved.
* IPv6: (none)
* IPv4: 3.210.66.237, 34.198.14.237, 44.212.132.255, 34.202.8.246, 34.204.155.59
*   Trying 3.210.66.237:80...
* Connected to hf.co (3.210.66.237) port 80
> GET /v2/bartowski/Replete-LLM-V2.5-Qwen-32b-GGUF/manifests/IQ4_NL HTTP/1.1
> Host: hf.co
> User-Agent: curl/8.7.1
> Accept:application/vnd.docker/distribution.manifest.v2+json
>
* Request completely sent off
< HTTP/1.1 302 Moved Temporarily
< Server: nginx/1.27.1
< Date: Fri, 25 Oct 2024 21:01:14 GMT
< Content-Type: text/html
< Content-Length: 145
< Connection: keep-alive
< Location: https://huggingface.co/v2/bartowski/Replete-LLM-V2.5-Qwen-32b-GGUF/manifests/IQ4_NL
< Access-Control-Allow-Origin: *
<
* Ignoring the response-body
* Connection #0 to host hf.co left intact
* Clear auth, redirects to port from 80 to 443
* Issue another request to this URL: 'https://huggingface.co/v2/bartowski/Replete-LLM-V2.5-Qwen-32b-GGUF/manifests/IQ4_NL'
* Host huggingface.co:443 was resolved.
* IPv6: 2600:9000:234c:c600:17:b174:6d00:93a1, 2600:9000:234c:c200:17:b174:6d00:93a1, 2600:9000:234c:0:17:b174:6d00:93a1, 2600:9000:234c:1200:17:b174:6d00:93a1, 2600:9000:234c:7400:17:b174:6d00:93a1, 2600:9000:234c:7200:17:b174:6d00:93a1, 2600:9000:234c:fa00:17:b174:6d00:93a1, 2600:9000:234c:6800:17:b174:6d00:93a1
* IPv4: 108.138.246.79, 108.138.246.71, 108.138.246.67, 108.138.246.85
*   Trying 108.138.246.79:443...
* Connected to huggingface.co (108.138.246.79) port 443
* ALPN: curl offers h2,http/1.1
* (304) (OUT), TLS handshake, Client hello (1):
*  CAfile: /etc/ssl/cert.pem
*  CApath: none
* (304) (IN), TLS handshake, Server hello (2):
* (304) (IN), TLS handshake, Unknown (8):
* (304) (IN), TLS handshake, Certificate (11):
* (304) (IN), TLS handshake, CERT verify (15):
* (304) (IN), TLS handshake, Finished (20):
* (304) (OUT), TLS handshake, Finished (20):
* SSL connection using TLSv1.3 / AEAD-AES128-GCM-SHA256 / [blank] / UNDEF
* ALPN: server accepted h2
* Server certificate:
*  subject: CN=huggingface.co
*  start date: May 13 00:00:00 2024 GMT
*  expire date: Jun 11 23:59:59 2025 GMT
*  subjectAltName: host "huggingface.co" matched cert's "huggingface.co"
*  issuer: C=US; O=Amazon; CN=Amazon RSA 2048 M03
*  SSL certificate verify ok.
* using HTTP/2
* [HTTP/2] [1] OPENED stream for https://huggingface.co/v2/bartowski/Replete-LLM-V2.5-Qwen-32b-GGUF/manifests/IQ4_NL
* [HTTP/2] [1] [:method: GET]
* [HTTP/2] [1] [:scheme: https]
* [HTTP/2] [1] [:authority: huggingface.co]
* [HTTP/2] [1] [:path: /v2/bartowski/Replete-LLM-V2.5-Qwen-32b-GGUF/manifests/IQ4_NL]
* [HTTP/2] [1] [user-agent: curl/8.7.1]
* [HTTP/2] [1] [accept: application/vnd.docker/distribution.manifest.v2+json]
> GET /v2/bartowski/Replete-LLM-V2.5-Qwen-32b-GGUF/manifests/IQ4_NL HTTP/2
> Host: huggingface.co
> User-Agent: curl/8.7.1
> Accept:application/vnd.docker/distribution.manifest.v2+json
>
* Request completely sent off
< HTTP/2 400
< content-type: text/plain; charset=utf-8
< content-length: 88
< date: Fri, 25 Oct 2024 21:01:14 GMT
< x-powered-by: huggingface-moon
< cross-origin-opener-policy: same-origin
< referrer-policy: strict-origin-when-cross-origin
< x-request-id: Root=1-671c071a-54fdb71444f06df2518f8e68
< x-error-message: The specified tag is not a valid quantization scheme. Please use another tag or "latest"
< etag: W/"58-hNaJEASla8mueALdqkDZntbiFuc"
< x-cache: Error from cloudfront
< via: 1.1 518f46e79d9e7fee6a625c5924750956.cloudfront.net (CloudFront)
< x-amz-cf-pop: SFO5-P1
< x-amz-cf-id: FI_gxXPG4tPoJqDbQlEZGH0maVYlpbKIoSvqtf0Vlqz8ACHUmWnhcw==
<
* Connection #1 to host huggingface.co left intact
The specified tag is not a valid quantization scheme. Please use another tag or "latest"%
<!-- gh-comment-id:2438831518 --> @mxyng commented on GitHub (Oct 25, 2024): > The specified tag is not a valid quantization scheme. Please use another tag or "latest" This error is not emitted by Ollama nor does Ollama validate quantization based on file name. The upstream, Hugging Face in this case, is refusing to serve the file. I suggest you open the issue with them. ``` $ curl -vL -H Accept:application/vnd.docker/distribution.manifest.v2+json hf.co/v2/bartowski/Replete-LLM-V2.5-Qwen-32b-GGUF/manifests/IQ4_NL * Host hf.co:80 was resolved. * IPv6: (none) * IPv4: 3.210.66.237, 34.198.14.237, 44.212.132.255, 34.202.8.246, 34.204.155.59 * Trying 3.210.66.237:80... * Connected to hf.co (3.210.66.237) port 80 > GET /v2/bartowski/Replete-LLM-V2.5-Qwen-32b-GGUF/manifests/IQ4_NL HTTP/1.1 > Host: hf.co > User-Agent: curl/8.7.1 > Accept:application/vnd.docker/distribution.manifest.v2+json > * Request completely sent off < HTTP/1.1 302 Moved Temporarily < Server: nginx/1.27.1 < Date: Fri, 25 Oct 2024 21:01:14 GMT < Content-Type: text/html < Content-Length: 145 < Connection: keep-alive < Location: https://huggingface.co/v2/bartowski/Replete-LLM-V2.5-Qwen-32b-GGUF/manifests/IQ4_NL < Access-Control-Allow-Origin: * < * Ignoring the response-body * Connection #0 to host hf.co left intact * Clear auth, redirects to port from 80 to 443 * Issue another request to this URL: 'https://huggingface.co/v2/bartowski/Replete-LLM-V2.5-Qwen-32b-GGUF/manifests/IQ4_NL' * Host huggingface.co:443 was resolved. * IPv6: 2600:9000:234c:c600:17:b174:6d00:93a1, 2600:9000:234c:c200:17:b174:6d00:93a1, 2600:9000:234c:0:17:b174:6d00:93a1, 2600:9000:234c:1200:17:b174:6d00:93a1, 2600:9000:234c:7400:17:b174:6d00:93a1, 2600:9000:234c:7200:17:b174:6d00:93a1, 2600:9000:234c:fa00:17:b174:6d00:93a1, 2600:9000:234c:6800:17:b174:6d00:93a1 * IPv4: 108.138.246.79, 108.138.246.71, 108.138.246.67, 108.138.246.85 * Trying 108.138.246.79:443... * Connected to huggingface.co (108.138.246.79) port 443 * ALPN: curl offers h2,http/1.1 * (304) (OUT), TLS handshake, Client hello (1): * CAfile: /etc/ssl/cert.pem * CApath: none * (304) (IN), TLS handshake, Server hello (2): * (304) (IN), TLS handshake, Unknown (8): * (304) (IN), TLS handshake, Certificate (11): * (304) (IN), TLS handshake, CERT verify (15): * (304) (IN), TLS handshake, Finished (20): * (304) (OUT), TLS handshake, Finished (20): * SSL connection using TLSv1.3 / AEAD-AES128-GCM-SHA256 / [blank] / UNDEF * ALPN: server accepted h2 * Server certificate: * subject: CN=huggingface.co * start date: May 13 00:00:00 2024 GMT * expire date: Jun 11 23:59:59 2025 GMT * subjectAltName: host "huggingface.co" matched cert's "huggingface.co" * issuer: C=US; O=Amazon; CN=Amazon RSA 2048 M03 * SSL certificate verify ok. * using HTTP/2 * [HTTP/2] [1] OPENED stream for https://huggingface.co/v2/bartowski/Replete-LLM-V2.5-Qwen-32b-GGUF/manifests/IQ4_NL * [HTTP/2] [1] [:method: GET] * [HTTP/2] [1] [:scheme: https] * [HTTP/2] [1] [:authority: huggingface.co] * [HTTP/2] [1] [:path: /v2/bartowski/Replete-LLM-V2.5-Qwen-32b-GGUF/manifests/IQ4_NL] * [HTTP/2] [1] [user-agent: curl/8.7.1] * [HTTP/2] [1] [accept: application/vnd.docker/distribution.manifest.v2+json] > GET /v2/bartowski/Replete-LLM-V2.5-Qwen-32b-GGUF/manifests/IQ4_NL HTTP/2 > Host: huggingface.co > User-Agent: curl/8.7.1 > Accept:application/vnd.docker/distribution.manifest.v2+json > * Request completely sent off < HTTP/2 400 < content-type: text/plain; charset=utf-8 < content-length: 88 < date: Fri, 25 Oct 2024 21:01:14 GMT < x-powered-by: huggingface-moon < cross-origin-opener-policy: same-origin < referrer-policy: strict-origin-when-cross-origin < x-request-id: Root=1-671c071a-54fdb71444f06df2518f8e68 < x-error-message: The specified tag is not a valid quantization scheme. Please use another tag or "latest" < etag: W/"58-hNaJEASla8mueALdqkDZntbiFuc" < x-cache: Error from cloudfront < via: 1.1 518f46e79d9e7fee6a625c5924750956.cloudfront.net (CloudFront) < x-amz-cf-pop: SFO5-P1 < x-amz-cf-id: FI_gxXPG4tPoJqDbQlEZGH0maVYlpbKIoSvqtf0Vlqz8ACHUmWnhcw== < * Connection #1 to host huggingface.co left intact The specified tag is not a valid quantization scheme. Please use another tag or "latest"% ```
GiteaMirror commented 2026-04-22 10:03:44 -05:00
Author
Owner
Copy Link

@fxmbsw7 commented on GitHub (Oct 25, 2024):

< x-cache: Error from cloudfront

<!-- gh-comment-id:2438972820 --> @fxmbsw7 commented on GitHub (Oct 25, 2024): < x-cache: Error from cloudfront
GiteaMirror commented 2026-04-22 10:03:45 -05:00
Author
Owner
Copy Link

@robbiemu commented on GitHub (Oct 26, 2024):

it is interesting, in both these cases the models did generate the bubbles for the quantization.
Captura de Tela 2024-10-26 às 8 38 05 AM

<!-- gh-comment-id:2439569189 --> @robbiemu commented on GitHub (Oct 26, 2024): it is interesting, in both these cases the models did generate the bubbles for the quantization. <img width="369" alt="Captura de Tela 2024-10-26 às 8 38 05 AM" src="https://github.com/user-attachments/assets/d557718d-581d-4fe6-bb11-b024006c9eac">
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#30441
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?