tinygrad/tinygrad
2
0
Fork 3
mirror of https://github.com/tinygrad/tinygrad.git synced 2026-08-29 10:16:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

cli: pin qwen3.8:27b to the pre-UD revision

Browse Source 
the UD-IQ4_XS replacement mixes in Q3_K tensors (ggml type 11) the loader
doesn't support; the pinned revision is byte-identical to the known-good file
This commit is contained in:
geohot
2026-08-23 10:49:14 -07:00
parent 983a369830
commit 359f7a5d43
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tinygrad/llm/cli.py
+2 -1
View File
@@ -88,7 +88,8 @@ models = {
"qwen3.5:9b": "https://huggingface.co/unsloth/Qwen3.5-9B-GGUF/resolve/main/Qwen3.5-9B-Q4_K_M.gguf",
"qwen3.6:27b": "https://huggingface.co/unsloth/Qwen3.6-27B-GGUF/resolve/main/Qwen3.6-27B-IQ4_XS.gguf",
"qwen3.6:35b-a3b": "https://huggingface.co/unsloth/Qwen3.6-35B-A3B-GGUF/resolve/main/Qwen3.6-35B-A3B-UD-Q4_K_M.gguf",
"qwen3.8:27b": "https://huggingface.co/unsloth/Qwen3.8-27B-GGUF/resolve/main/Qwen3.8-27B-UD-IQ4_XS.gguf",
# pinned to the last revision with the plain IQ4_XS quant: the UD replacement uses Q3_K tensors the loader doesn't support
"qwen3.8:27b": "https://huggingface.co/unsloth/Qwen3.8-27B-GGUF/resolve/b62a80264f8b0c1bb849ee1c9c487415ebeca194/Qwen3.8-27B-IQ4_XS.gguf",
"olmoe": "https://huggingface.co/allenai/OLMoE-1B-7B-0924-Instruct-GGUF/resolve/main/olmoe-1b-7b-0924-instruct-q4_k_m.gguf",
"moonlight": "https://huggingface.co/gabriellarson/Moonlight-16B-A3B-Instruct-GGUF/resolve/main/Moonlight-16B-A3B-Instruct-Q4_K_M.gguf",
"glm-4.7-flash": "https://huggingface.co/unsloth/GLM-4.7-Flash-GGUF/resolve/main/GLM-4.7-Flash-Q4_K_M.gguf",