Transformers
GGUF
programming
code generation
code
codeqwen
Mixture of Experts
coding
coder
qwen2
chat
qwen
qwen-coder
Qwen3-Coder-30B-A3B-Instruct
Qwen3-30B-A3B
mixture of experts
128 experts
8 active experts
768k context
qwen3
finetune
brainstorm 20x
brainstorm
optional thinking
qwen3_moe
conversational
auto-patch README.md
Browse files
README.md
CHANGED
@@ -59,7 +59,7 @@ static quants of https://huggingface.co/DavidAU/Qwen3-Coder-42B-A3B-Instruct-TOT
|
|
59 |
|
60 |
***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx-GGUF).***
|
61 |
|
62 |
-
weighted/imatrix quants
|
63 |
## Usage
|
64 |
|
65 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
@@ -76,9 +76,11 @@ more details, including on how to concatenate multi-part files.
|
|
76 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx-GGUF/resolve/main/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx.Q3_K_S.gguf) | Q3_K_S | 18.5 | |
|
77 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx-GGUF/resolve/main/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx.Q3_K_M.gguf) | Q3_K_M | 20.5 | lower quality |
|
78 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx-GGUF/resolve/main/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx.Q3_K_L.gguf) | Q3_K_L | 22.1 | |
|
|
|
79 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx-GGUF/resolve/main/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx.Q4_K_S.gguf) | Q4_K_S | 24.3 | fast, recommended |
|
80 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx-GGUF/resolve/main/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx.Q4_K_M.gguf) | Q4_K_M | 25.8 | fast, recommended |
|
81 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx-GGUF/resolve/main/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx.Q5_K_S.gguf) | Q5_K_S | 29.3 | |
|
|
|
82 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx-GGUF/resolve/main/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx.Q6_K.gguf) | Q6_K | 34.9 | very good quality |
|
83 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx-GGUF/resolve/main/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx.Q8_0.gguf) | Q8_0 | 45.2 | fast, best quality |
|
84 |
|
|
|
59 |
|
60 |
***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx-GGUF).***
|
61 |
|
62 |
+
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx-i1-GGUF
|
63 |
## Usage
|
64 |
|
65 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
|
76 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx-GGUF/resolve/main/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx.Q3_K_S.gguf) | Q3_K_S | 18.5 | |
|
77 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx-GGUF/resolve/main/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx.Q3_K_M.gguf) | Q3_K_M | 20.5 | lower quality |
|
78 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx-GGUF/resolve/main/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx.Q3_K_L.gguf) | Q3_K_L | 22.1 | |
|
79 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx-GGUF/resolve/main/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx.IQ4_XS.gguf) | IQ4_XS | 23.0 | |
|
80 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx-GGUF/resolve/main/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx.Q4_K_S.gguf) | Q4_K_S | 24.3 | fast, recommended |
|
81 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx-GGUF/resolve/main/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx.Q4_K_M.gguf) | Q4_K_M | 25.8 | fast, recommended |
|
82 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx-GGUF/resolve/main/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx.Q5_K_S.gguf) | Q5_K_S | 29.3 | |
|
83 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx-GGUF/resolve/main/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx.Q5_K_M.gguf) | Q5_K_M | 30.2 | |
|
84 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx-GGUF/resolve/main/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx.Q6_K.gguf) | Q6_K | 34.9 | very good quality |
|
85 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx-GGUF/resolve/main/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-768k-ctx.Q8_0.gguf) | Q8_0 | 45.2 | fast, best quality |
|
86 |
|