---
license: apache-2.0
language:
  - en
base_model: cloudsurf-software/CloudSurf-4B-FC
base_model_relation: quantized
pipeline_tag: text-generation
library_name: llama.cpp
model_name: CloudSurf-4B-FC
tags:
  - gguf
  - llama.cpp
  - function-calling
  - tool-use
  - bfcl
  - cloudsurf
  - gemma-4
  - conversational
inference: false
---

# CloudSurf-4B-FC — official GGUF quants

Official GGUF quantizations of
[CloudSurf-4B-FC](https://huggingface.co/cloudsurf-software/CloudSurf-4B-FC),
a Gemma-4 E4B (effective-4B active; ~8.0B total params) function-calling /
tool-use model by CloudSurf Software, quantized by us from the BF16 merged
champion checkpoint. All benchmark scores, training details, and honesty
disclosures live in the
[base model card](https://huggingface.co/cloudsurf-software/CloudSurf-4B-FC)
— the scores there were measured on the **BF16** weights, not on these
quants. A quantized-model eval is pending and will be added here when it
lands; until then, assume some quality loss below Q8_0, growing as the
bit-width shrinks.

Every model file in this repo passed a 6-case tool-call smoke suite
(simple call, multi-argument, tool selection, `role:tool` round-trip,
irrelevance refusal, parallel calls) against `llama-server --jinja` before
upload. A file that fails any case does not ship.

## Files

| File | Size | Use case | Tool-call smoke |
|------|------|----------|-----------------|
| [CloudSurf-4B-FC.Q4_K_M.gguf](https://huggingface.co/cloudsurf-software/CloudSurf-4B-FC-GGUF/resolve/main/CloudSurf-4B-FC.Q4_K_M.gguf) | 5.3 GB | **Recommended default** — fits 8 GB RAM/VRAM | 6/6 PASS (2026-08-19) |
| [CloudSurf-4B-FC.Q5_K_M.gguf](https://huggingface.co/cloudsurf-software/CloudSurf-4B-FC-GGUF/resolve/main/CloudSurf-4B-FC.Q5_K_M.gguf) | 5.8 GB | Balanced quality/size | 6/6 PASS (2026-08-19) |
| [CloudSurf-4B-FC.Q6_K.gguf](https://huggingface.co/cloudsurf-software/CloudSurf-4B-FC-GGUF/resolve/main/CloudSurf-4B-FC.Q6_K.gguf) | 6.2 GB | Quality pick for 8GB VRAM | 6/6 PASS (2026-08-19) |
| [CloudSurf-4B-FC.Q8_0.gguf](https://huggingface.co/cloudsurf-software/CloudSurf-4B-FC-GGUF/resolve/main/CloudSurf-4B-FC.Q8_0.gguf) | 8.0 GB | Near-lossless | 6/6 PASS (2026-08-19) |
| [CloudSurf-4B-FC.Q3_K_M.gguf](https://huggingface.co/cloudsurf-software/CloudSurf-4B-FC-GGUF/resolve/main/CloudSurf-4B-FC.Q3_K_M.gguf) | 4.9 GB | Low-RAM entry point | 6/6 PASS (2026-08-19) |
| [CloudSurf-4B-FC.BF16.gguf](https://huggingface.co/cloudsurf-software/CloudSurf-4B-FC-GGUF/resolve/main/CloudSurf-4B-FC.BF16.gguf) | 15.1 GB | Reference / requantize source | 6/6 PASS (2026-08-19) |

### Vision (mmproj)

Pair any quant with a projector file for image input:
[mmproj-CloudSurf-4B-FC.F16.gguf](https://huggingface.co/cloudsurf-software/CloudSurf-4B-FC-GGUF/resolve/main/mmproj-CloudSurf-4B-FC.F16.gguf)
(1.0 GB) or
[mmproj-CloudSurf-4B-FC.Q8_0.gguf](https://huggingface.co/cloudsurf-software/CloudSurf-4B-FC-GGUF/resolve/main/mmproj-CloudSurf-4B-FC.Q8_0.gguf)
(0.6 GB):

```bash
llama-server -m CloudSurf-4B-FC.Q4_K_M.gguf --mmproj mmproj-CloudSurf-4B-FC.F16.gguf --jinja -ngl 99
```

Function calling is this model's primary capability; vision rides along from
the Gemma-4 base.

For imatrix (weighted) quants below Q3, see the community repo
[mradermacher/CloudSurf-4B-FC-i1-GGUF](https://huggingface.co/mradermacher/CloudSurf-4B-FC-i1-GGUF)
— an independent quantization of the same weights, credit to mradermacher
for the fast pickup.

SHA-256 checksums for every file are in
[`quant-manifest.json`](https://huggingface.co/cloudsurf-software/CloudSurf-4B-FC-GGUF/resolve/main/quant-manifest.json).

## Running

### llama.cpp (server, OpenAI-compatible tool calls)

`--jinja` is required — it enables the embedded chat template's tool-call
rendering. Without it the server falls back to a generic template and tool
calls will not parse.

```bash
llama-server -m CloudSurf-4B-FC.Q4_K_M.gguf --jinja -ngl 99 -c 16384 \
  --host 127.0.0.1 --port 8080 --alias cloudsurf-4b-fc
# then point any OpenAI client at http://127.0.0.1:8080/v1
# (chat/completions with tools in, tool_calls out)
```

### llama.cpp (CLI)

```bash
llama-cli -m CloudSurf-4B-FC.Q4_K_M.gguf --jinja -ngl 99 -c 16384 \
  -p "You are a helpful assistant." -cnv
```

### LM Studio

Search for `CloudSurf-4B-FC-GGUF` in the in-app model browser and download
a quant. Enable the model's own prompt template (default) and use the
OpenAI-compatible local server for tool calls.

### Ollama

```bash
cat > Modelfile <<'EOF'
FROM ./CloudSurf-4B-FC.Q4_K_M.gguf
EOF
ollama create cloudsurf-4b-fc -f Modelfile
ollama run cloudsurf-4b-fc
```

The GGUF's embedded chat template carries the tool-call format; recent
Ollama versions read it directly.

## Notes and known quirks

- **Scores**: the base card's BFCL V4 numbers (3-seed mean 55.73
  as-registered / 54.91 matched-variant — both frames disclosed there) are
  BF16 measurements. No number in that card applies to these quants until
  the pending quantized-model eval is published here.
- **Params**: "4B" is effective active parameters (the base's E4B
  convention); total is ~8.0B, which is what sizes these files.
- **`</s>` metadata quirk**: GGUF conversions of this model can carry a
  stray `</s>` end-token metadata entry; llama.cpp detects and auto-corrects
  it at load (benign — observed and verified 2026-08-18).
- **Context**: trained/evaluated at 131K-class context; `-c 16384` above is
  a practical default, raise as your memory allows.

## License

Apache-2.0, same as the base model. Gemma-4 base weights are subject to
Google's Gemma terms as described in the base model card.