[GH-ISSUE #10504] Using a custom model fails with file does not exist error #6911

Closed
opened 2026-04-12 18:48:06 -05:00 by GiteaMirror · 0 comments
Owner

Originally created by @aphilas on GitHub (Apr 30, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10504

What is the issue?

$ ollama --version
ollama version is 0.6.6

$ cat models/gemma-3-4b-it-qat-q4_0/Modelfile 
FROM ./gemma-3-4b-it-qat-q4_0.gguf
TEMPLATE """{{- range $i, $_ := .Messages }}
{{- $last := eq (len (slice $.Messages $i)) 1 }}
{{- if or (eq .Role "user") (eq .Role "system") }}<start_of_turn>user
{{ .Content }}<end_of_turn>
{{ if $last }}<start_of_turn>model
{{ end }}
{{- else if eq .Role "assistant" }}<start_of_turn>model
{{ .Content }}{{ if not $last }}<end_of_turn>
{{ end }}
{{- end }}
{{- end }}
"""
PARAMETER stop <end_of_turn>
PARAMETER temperature 1
PARAMETER top_k 64
PARAMETER top_p 0.95

$ ollama create -f ./models/gemma-3-4b-it-qat-q4_0/Modelfile gemma-3-4b-it-qat-q4_0
gathering model components 
copying file sha256:76aed0a8285b83102f18b5d60e53c70d09eb4e9917a20ce8956bd546452b56e2 100% 
parsing GGUF 
using existing layer sha256:76aed0a8285b83102f18b5d60e53c70d09eb4e9917a20ce8956bd546452b56e2 
using existing layer sha256:5be6630b666f007a127a456fb3958da5fbd7cf547204188bc4690fedc837af0b 
using existing layer sha256:3116c52250752e00dd06b16382e952bd33c34fd79fc4fe3a5d2c77cf7de1b14b 
writing manifest 
success 

$ ollama ls
NAME                             ID              SIZE      MODIFIED       
gemma-3-4b-it-qat-q4_0:latest    3afec082aa87    3.2 GB    18 seconds ago

$ ollama run gemma-3-4b-it-qat-q4_0
pulling manifest 
Error: pull model manifest: file does not exist

$ ollama run gemma-3-4b-it-qat-q4_0:latest
pulling manifest 
Error: pull model manifest: file does not exist

Relevant log output

Apr 30 18:34:08 nile ollama[18764]: time=2025-04-30T18:34:08.190+03:00 level=ERROR source=images.go:92 msg="couldn't open model file" error="open : no such file or directory"

OS

Linux

GPU

No response

CPU

Intel

Ollama version

0.6.6

Originally created by @aphilas on GitHub (Apr 30, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10504 ### What is the issue? ``` $ ollama --version ollama version is 0.6.6 $ cat models/gemma-3-4b-it-qat-q4_0/Modelfile FROM ./gemma-3-4b-it-qat-q4_0.gguf TEMPLATE """{{- range $i, $_ := .Messages }} {{- $last := eq (len (slice $.Messages $i)) 1 }} {{- if or (eq .Role "user") (eq .Role "system") }}<start_of_turn>user {{ .Content }}<end_of_turn> {{ if $last }}<start_of_turn>model {{ end }} {{- else if eq .Role "assistant" }}<start_of_turn>model {{ .Content }}{{ if not $last }}<end_of_turn> {{ end }} {{- end }} {{- end }} """ PARAMETER stop <end_of_turn> PARAMETER temperature 1 PARAMETER top_k 64 PARAMETER top_p 0.95 $ ollama create -f ./models/gemma-3-4b-it-qat-q4_0/Modelfile gemma-3-4b-it-qat-q4_0 gathering model components copying file sha256:76aed0a8285b83102f18b5d60e53c70d09eb4e9917a20ce8956bd546452b56e2 100% parsing GGUF using existing layer sha256:76aed0a8285b83102f18b5d60e53c70d09eb4e9917a20ce8956bd546452b56e2 using existing layer sha256:5be6630b666f007a127a456fb3958da5fbd7cf547204188bc4690fedc837af0b using existing layer sha256:3116c52250752e00dd06b16382e952bd33c34fd79fc4fe3a5d2c77cf7de1b14b writing manifest success $ ollama ls NAME ID SIZE MODIFIED gemma-3-4b-it-qat-q4_0:latest 3afec082aa87 3.2 GB 18 seconds ago $ ollama run gemma-3-4b-it-qat-q4_0 pulling manifest Error: pull model manifest: file does not exist $ ollama run gemma-3-4b-it-qat-q4_0:latest pulling manifest Error: pull model manifest: file does not exist ``` ### Relevant log output ```shell Apr 30 18:34:08 nile ollama[18764]: time=2025-04-30T18:34:08.190+03:00 level=ERROR source=images.go:92 msg="couldn't open model file" error="open : no such file or directory" ``` ### OS Linux ### GPU _No response_ ### CPU Intel ### Ollama version 0.6.6
GiteaMirror added the bug label 2026-04-12 18:48:06 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#6911